Master thesis motion analysis from encoded video bitstream

Contributions The thesis proposes a new moving object detection method in surveillance video encoded with H264 compression standard using the motion vector and size of macroblock... Cha

VIETNAM NATIONAL UNIVERSITY, HANOI

UNIVERSITY OF ENGINEERING AND TECHNOLOGY

NGUYEN MINH HOA

MOTION ANALYSIS FROM ENCODED VIDEO

BITSTREAM

MASTER’S THESIS

HA NOI – 2018

VIETNAM NATIONAL UNIVERSITY, HANOI

UNIVERSITY OF ENGINEERING AND TECHNOLOGY

NGUYEN MINH HOA

MOTION ANALYSIS FROM ENCODED VIDEO

AUTHORSHIP

“I hereby declare that the work contained in this thesis is of my own and I have

not submitted this thesis at any other institution in order to obtain a degree To the best of my knowledge and belief, the thesis contains no materials previously published or written by another person other than those listed in the bibliography and identified as references.”

Signature: ………

SUPERVISOR’S APPROVAL

“I hereby approve that the thesis in its current form is ready for committee

examination as a requirement for the Master of Computer Science degree at the University of Engineering and Technology.”

Signature: ………

Signature: ………

ACKNOWLEDGMENTS

First of all, I would like to express special gratitude to my supervisors, Dr Do Van Nguyen and Dr Tran Quoc Long, for their enthusiasm for instructions, the technical explanation as well as advices during this project

I also want to give sincere thanks to Assoc Prof Dr Ha Le Thanh, Assoc Prof

Dr Nguyen Thi Thuy for the instructions as well as the background knowledge for this thesis And I would like to also thank my teachers, my friends in Human Machine Interaction Lab for their support

Thank my friends, my colleagues in the project "Nghiên Cứu Công Nghệ Tóm Tắt

Video", and project “Multimedia application tools for intangible cultural heritage conservation and promotion”, project number ĐTDL.CN-34/16 for their working

and support

Last but not least, I want to thank my family and all of my friends for their motivation and support as well They stand by and inspire me whenever I face the tough time

TABLE OF CONTENTS

AUTHORSHIP i

SUPERVISOR’S APPROVAL ii

ACKNOWLEDGMENTS iii

TABLE OF CONTENTS 1

ABBREVIATIONS 3

List of Figures 4

List of Tables 5

INTRODUCTION 6

CHAPTER 1 LITERATURE REVIEW 9

Moving object detection in the pixel domain 9

Moving object detection in the compressed domain 10

1.2.1 Motion vector approaches 11

1.2.2 Size of Macroblock approaches 13

Chapter Summarization 14

CHAPTER 2 METHODOLOGY 15

Video compression standard h264 15

2.1.1 H264 file structure 15

2.1.2 Macroblock 18

2.1.3 Motion vector 19

Proposed method 21

2.2.1 Process video bitstream 21

2.2.2 Macroblock-based Segmentation 22

2.2.3 Object-based Segmentation 24

2.2.4 Object Refinement 28

Chapter Summarization 28

CHAPTER 3 RESULTS 30

The moving object detection application 30

3.1.1 The process of application 31

3.1.2 The motion information 34

3.1.3 Synthesizing movement information 35

3.1.4 Storing Movement Information 36

Experiments 36

3.2.1 Dataset 36

3.2.2 Evaluation methods 40

3.2.3 Implementations 41

3.2.4 Experimental results 41

Chapter Summarization 44

CONCLUSIONS 45

List of of author’s publications related to thesis 46

REFERENCES 47

List of Figures

Figure 1.1 The process of moving object detection with data in the pixel domain

10

Figure 1.2 The process of moving object detection with data in the compressed domain 11

Figure 2.1 The structure of a H264 file 15

Figure 2.2 RBSP structure 16

Figure 2.3 Slide structure 18

Figure 2.4 Macroblock structure 18

Figure 2.5 The motion vector of a Macroblock 20

Figure 2.6 The process of moving object detection method 22

Figure 2.7 Skipped Macroblock 23

Figure 2.8 (a) An outdoor and in-door frames (b) The "size-map" of frames, (c) The "motion-map" of frames 24

Figure 2.9 Example about the “consistent” of motion vector 26

Figure 3.1 The implementation process of the approach 33

Figure 3.2 Data struct to storage motion information 35

Figure 3.3 Example frames of test videos 37

Figure 3.4 Example frames and their ground truth 39

Figure 3.5 An example frame of Pedestrians (a) and ground truth image (b) 40

List of Tables

Table 2.1 NALU types 16

Table 2.2 Slide types 17

Table 3.1 The information of test videos 38

Table 3.2 The information of test sequences in group 1 39

Table 3.3 The performance of two approachs with Pedestrians, PETS2006, Highway, and Office 42

Table 3.4 The experimental result of Poppe’s approach on 2nd group 42

Table 3.5 The experimental result of proposed method on 2nd group 43

INTRODUCTION

Today, video content is extensively used in the areas of life such as indoor monitoring, traffic monitoring, etc The number of videos sharing over the Internet at any given time is also extremely large According to statistics, hundreds of hours of video are uploaded to Youtube every minute [1] Not only that, the general trend today is the surveillance cameras installed in homes for surveillance and sercurity purposes These cameras will normally operate and store the surveillance videos automatically Only when there are some special situations, or some special events occur, humans will use the video data to revisit The problem is that in a short amount of time, how can such a large video volume

be evaluated? For example, when there is a burglary, an intrusion occurs, we can not spend hours to check each video previously stored Then, a tool that lets you determine the moment when an object is moving in a long video is essential to reducing the time and effort of searching

Normally, in order to reduce the size of videos for transmission or storing, a video compression procedure is performed at surveillance cameras After that, the compressed information in form of bit stream is stored, or transmitted to a server for analysis The video analysis process needs a lot of features to describe different aspects of vision Typically, these features are extracted from the pixel values of each video frame by fully decompressing bitstream The decompression procedure requires high computation capacity device to perform However, with the trend of "Internet of Things", there are many low processing capacity devices which are not capable for performing this full video decompression at high speed

So, it is difficult to perform an approach that requires a lot of computing power in real time

Another way to extract the feature from the video is using the data on the compressed video These data can be: transform coefficients, motion vectors, quantization steps, quantization parameters, etc From the above data, through the process and analysis, we can handle some important tasks in the computer vision include moving objects detection, human actions detection, face recognition, motion objects tracking

This thesis proposes a new method to determine moving object by exploring and applying some motion estimation techniques in the video compression domain After that, the method will be used to build an application that supports movement searching in the surveillance videos in the families The compression format of

the videos in the thesis is the H264 compression standard (MPEG-4 part10), a popular video compression standard today

Aims

The goal of the thesis is to propose a method for determining moving objects in the compressed domain of a video Then, I try to build an application using the method for support searching the moments which have moving objects in the video

Object and Scope of the study

Within the framework of the thesis, I study the algorithms related to determining moving objects in video, especially the algorithms that determine moving objects

in the compressed domain The video compression standard is used in the thesis

is H264/AVC

The theory of video compression and computer vision are taken from scientific articles related to the video analysis problem on the compression domain, determine the motion form on the compression domain of the video

The videos for test and experiment are obtained from the surveillance cameras both indoor and outdoor

Method and procedures

- Research on motion analysis and evaluation systems on existing compressed video, scientific articles related to the analysis and evaluation of motion on compressed video

- Experimental research: Conduct experiential settings for each theoretical part such as extracting video data, compiling data, and evaluating motion based on the obtained data

- Experimental evaluation: Each experiment will be conducted independently on each module and then integrated and deployed

Contributions

The thesis proposes a new moving object detection method in surveillance video encoded with H264 compression standard using the motion vector and size of macroblock

Chapter 2 mentiones the basic knowledge about video compression standard H264 such as H264 file structure, macroblocks, motion vectors and describes the detail of moving object detection method including processing video bitstreams, macroblock-based segmentation phase, object-based segmentation phase, and object refinement phase

Chapter 3 shows the results of method including an application using proposed method and experimental results

CHAPTER 1

LITERATURE REVIEW

Today, surveillance cameras are used extensively in the world The volume of video surveillance has also grown tremendously Some problems that are often encountered with video surveillance include event searching, motion tracking, abnormal behavior detection, etc In order to handle these tasks, it is necessary to have a method that can determine which the moments in each videos exist movements

Usually, the video is compressed for storage and transmission The previous moving object detection method usually use the data from the pixel images such

as color value, edges, etc To get the images that can be displayed, or processed, the system must decode video fully This consumes a large number of computing resources, time and memory of the device I suggest a method that can quickly determine the moving objects in high resolution videos The data used in the method will be taken from the compressed video domain including information about the motion vector and the size of the macroblock (in bit) after encoding The method reduces the processing time of the method considerably compared to methods implemented with data on the pixel domain

The problem of motion detection in a video has long been studied This is the first step in a series of computer vision problems such as object tracking, object detection, abnormal movement detection, etc There are usually two approaches

to address this problem: using fully decoded video data (pixel domain data) or using live data from an undecoded video (compressed domain data) The following section will outline the studies based on these two approaches

Moving object detection in the pixel domain

Typically, to reduce the size of the video for transmission, a video encoding process is performed inside the surveillance camera and the compressed information is transmitted as a bit stream to a server for video analysis Common video compression standards used today including mp4, H264, H265 To be viewable, these compressed videos need to be decoded to image frames We call these image frames are the pixel domain and the data obtained from these image frames are the data in the pixel domain Fig 1.1 describes the process of moving object detection methods in the pixel domain The data in the pixel domain include the color values of the pixels, the number of color channels of each pixel, the edges, etc

Figure 1.1 The process of moving object detection with data in the pixel domain

To determine moving objects in the pixel domain, background subtraction algorithms are commonly used There are many research results that have been introduced long ago These methods usually use data as the relationship between frames in a time series

Background subtraction in [2] is defined as: “Background subtraction is a widely used approach for detecting moving objects in videos from static cameras The rationale in the approach is that of detecting the moving objects from the difference between the current frame and a reference frame, often called The

“background image”, or “background model” As a basic, the background image must be a representation of the scene with no moving objects and must be kept regularly updated so as to adapt to the varying luminarice conditions and geometry settings.”

Results of the researchs may include the methods use Gaussian average such as the method of Wren et al [3], the method of Koller et al [4]; the methods use Temporal median filter such as the method of Lo and Velasti [5], the method of Cucchiara et al [6]; the methods using a mixture of Gaussians such as the method

of Stauffer and Grimson [7], methods of Wayne Power and Schoonees [8]; etc The above methods have a common characteristic that is the process data are taken

by fully decompress the compressed bitstream and this decompression procedure requires a highly computational device to perform However, with the trend of

"Internet of Things," where most low-end devices are not capable of performing high-speed decompression Therefore, there should be a video analysis mechanism that includes only uncompressed video

Moving object detection in the compressed domain

Normally, the videos will be encoded using some compression standard Each compression standard specifies how to shrink the video size by a certain structure The compressed videos will contain fewer data For example, with the H264 compression standard, the data contained in the compressed video includes

information about macroblock, motion vector, frame information, etc We call these data that the data in the compressed domain or video compression region Fig 1.2 shows the process of moving object detection methods by using the data

in the compressed domain

Figure 1.2 The process of moving object detection with data in the compressed

domain

In general, the amount of data in the video compression domain is much less than the data in the pixel domain The idea of using data in the compressed domain with the H264 compression standard for video analysis has also been investigated

by some scientists around the world In order to be able to detect motion in the compressed video domain, we usually use two types of data They are the motion vector and the size (in bit) of the macroblock

1.2.1 Motion vector approaches

A number of algorithms have been proposed to analyze video content in the H264 compressed domain, whose good performances have been obtained [9] [10] Zeng

et al Study in [11] proposed a method to detect moving objects in H264 compressed videos based on motion vectors Motion vectors are extracted from the motion field and classified into several types Then, they are grouped into blocks through the Markov Random Field (MRF) classification process Liu et al [12] recognized the shape of an object by using a map for each object This approach is based on a binary partition tree created by macroblocks Cipres et al [13] presented a moving object detection approach in the H264 compressed domain based on fuzzy logic The motion vectors are used to remove the noises that appear during the encoding process and represent the concepts that describe the detected regions Then, the valid motion vectors are grouped into blocks Each

of them could be identified as a moving object in the video scene The moving objects of each frame are described with common terms like shape, size, position, and velocity Mak et al [14] used the length, angle, and direction of motion vectors to track the objects by applying the MRF Bruyne et al [15] estimated the

reliability of motion vectors by comparing them with projected motion vectors from surrounding frames Then, they combined this information with the magnitude of motion vectors to distinguish foreground objects from the background This method can localize the noisy motion vectors and their effect during the classification can be diminished Wang et al [16] proposed a background modeling method using the motion vector and local binary pattern (LBP) to detect the moving object When a background block was similar to a foreground block, a noisy motion vector would appear To obtain a more reliable and dense motion vector field, the initial motion vector fields were preprocessed

by a temporal accumulation within three inter frames and a 3×3 median filtering After that, the LBP feature was introduced to describe the spatial correlation among neighboring blocks This approach can reduce the time of extracting moving objects while also performing an effective synopsis analysis Marcus Laumer [17] proposed an approach to segment video frames into the foreground and background and, according to this segmentation, to identify regions containing moving objects The approach uses a map to indicate the "weight" of each (sub-)macroblock for the presence of a moving object This map is the input

of a new spatiotemporal detection algorithm that is used to refine the weight that indicated the level of motion for each block Then, quantization parameters of macroblocks are used to apply individual thresholds to the block weights to segment the video frames The accuracy of the approach was approximately 50%

To identify the human action, Tom et al [18] proposed a quick action identification algorithm The algorithm uses quantization parameters gradient image (QGI) and motion vectors with support vector machines (SVM) to classify the types of the actions The algorithm can also handle light, scale and some other environmental variables with an accuracy rate of 85% on the videos with resolution 176x144 It can identifies walking, running, etc Similarly, Tom, Rangarajan and his colleagues also used QGI and motion vector to propose a new method to classify human actions as the Projection Based Learning of the Meta-cognitive Radial Basis Functional Network (PBL-McRBFN)

With the motion tracking problem, Biswas et al [19] propose a method for detecting abnormal actions by analyzing motion vector This method mainly relies

on observing the motion vector to find the difference between abnormal actions and normal situations The classifier used here is the Gaussian Mixture Model (GMM) This approach base on their another approach [20] but improved it by using the direction of the motion vector The speed of approach when perform experimental is about 70fps Thilak et al [21] propose a Probabilistic Data

Association Filter that detects multiple target clusters This method can handle cases in which targets split into multiple clusters or clusters should be detected (classified) as a target Similarly, You et al [22] use the probabilistic spatio-temporal MB filtering to mark the macroblock as objects and then remove them from the noise The algorithm can track many objects with real-time accuracy but can only be applied in case of fixed camera and objects must be at least two macroblocks Kas et al [23] overcame the fixed camera problem using Global Motion Estimation and Object History Images to handle background movement However, the number of motion objects need to be small and the moving objects are not occupied most of the frame area

1.2.2 Size of Macroblock approaches

The methods mentioned above share the trait of using motion vectors to detect moving objects However, since motion vectors are usually created at the video encoder to optimize video compression ratio, they do not always represent the real motion in the video sequence As such, due to its coding-oriented nature, to detect moving objects, the motion vector fields must be preprocessed and refined to remove the noises

So, Poppe et al [24] proposed an approach to detect moving objects in the H264 video by using the size of the macroblocks after encoding (in bit) To achieve Sub-macroblock-level (4×4) precision, the information from transform coefficients was also utilized The system achieved high execution speeds, up to 20 times faster than the motion vector-based related works An analysis was restricted to Predicted (P) frames, and a simple interpolation technique was employed to handle Intra (I) frames The whole algorithm was based on the assumption that the macroblocks that contains an edge of a moving object is more difficult to compress since it is hard to find a good match for those macroblocks in the reference frame(s)

Base on Poppe’s idea, Vacavant et al [25] used the macroblock size to detect moving objects by applying the Gaussian mixture model (GMM) The approach can represent the distribution of macroblock sizes well

Although the method of Poppe and Vacavant is good for removing the background motion noise, they cannot produce high motion detection results for videos in high spatial resolution (such as 1920 × 1080 or 1280 × 720) In case where the moving objects are large and they contain a uniform color region (such

as a black car), then the size of macroblocks corresponding to the inside region of

the moving object will be very small (normally around zero), and using a filtering threshold or parameter (though very small) will not be effective In those cases, the algorithm will determine these regions to be background

Chapter Summarization

In this chapter showed the researchs about moving object detection in both pixel domain and compressed domain The approachs using data from pixel domain usually have high accuracy but taking a large number of computing resources and time The approachs using data in compressed domain have lower accuracy because the data in compressed domain usually contain less information In the next chapters, I will propose a method that can efficiently detect moving objects, especially in high spatial resolution video streams The method uses the data taken from the video compressed domain, including the size of the macroblocks to detect the skeleton of the moving object and the motion vectors to detect the detail

of the moving object

CHAPTER 2

METHODOLOGY Video compression standard h264

Before proposing the moving object detection method, this chapter will show some informations about H264, a popular video compression standard, which is used to encode and decode the surveillance video in the thesis

This day, the installation of surveillance cameras in house became quite common Normally, video data from a surveillance camera over a long period of time usually has very huge size Consequently, videos need to be preprocessed and encoded before being used and transmitted over the network There are many recognized compression standards and widely used One of these is the H264 or MPEG-4 part 10 [26], a compression standard recognized by the ITU-T Video Coding Experts Group and the ISO/IEC Moving Picture Experts Group

2.1.1 H264 file structure

Normally, the video after being captured from the camera will be compressed using a common video compression standard such as H261, H263, MP4, H264/AVC, H265/HEVC, etc In the thesis, I encode and decode the video by using H264/AVC The H264 video codec or MPEG-4 part 10 is recognized by the ITU-T Video Coding Experts Group and the ISO/IEC Moving Picture Experts Group

Typically, an H264 file is splitted into packets called the Network Abstraction Layer Unit (NALU) [27], as shown in Fig 2.1

Figure 2.1 The structure of a H264 file

The first NALU byte indicates the type of NALU The NALU type shows what the NALU's structure is It can be a slice or set parameters for decompression The meaning of the NALU in Table 2.1

Table 2.1 NALU types

0 Undefined

1 Slice layer without partitioning non IDR

2 Slice data partition A layer

3 Slice data partition B layer

4 Slice data partition C layer

5 Slice layer without partitioning IDR

6 Additional information (SEI)

7 Sequence parameter set

8 Picture parameter set

9 Access unit delimiter

10 End of sequence

11 End of stream

12 Filler data 13 23 Reserved 24 31 Undefined Other than NALU, the rest of the NALU is called RBSP (Raw Byte Sequence Payload) RBSP contains data of SODB (String Of Data Bits) According to the specification document H264 (ISO/IEC 14496-10) if the SODB is empty (no bits are present), the RBSP is also empty The first byte of RBSP (left side) contains

8 bits of SODB; The next byte of the RBSP will contain up to 8 bits of SODB and continue until less than 8 bits of SODB

Figure 2.2 RBSP structure

A video will normally be divided into frames and the encoder will encode them one by one Each frame is encoded into slices Each slice is divided into Macroblock (MB) Typically, each frame corresponds to a slice, but sometimes a frame can be split into multiple slices The slices are divided into categories as shown in Fig 2.2 A slice consists of a header and a data section (Fig 2.3) The header of the slice contains information about the type of slice, the type of MB in the slice, the number of slice frames The header also contains information about the reference frame and quantitative parameters The data portion of the slice is the information about the macroblock

Table 2.2 Slide types

0 P-slice Consists of P-macroblocks (each macroblock is predicted using one reference frame) and/or I-macroblocks

1 B-slice Consists of B-macroblocks (each macroblock is predicted

using one or two reference frames) and/or I-macroblocks

2 I-slice Contains only I-macroblocks Each macroblock is predicted from previously coded blocks of the same slice

3 SP-slice Consists of P and/or I-macroblocks and lets you switch

between encoded streams

4 SI-slice It consists of a special type of SI-macroblocks and lets you switch between encoded streams

Figure 2.3 Slide structure

2.1.2 Macroblock

The basic principle of a compression standard is to split the video into frame groups Each frame is divided into the basic processing units (For example, in the H264/AVC standard, it is Macroblock (MB) which is a region 16x16 pixels) Also, with some data regions carrying more detail, the MBs will be subdivided into smaller sub-macroblocks (4x4 or 8x8 pixels) Each MB after compression will contain the information used to recover the video later, including Motion vector, Residual value, Quantization parameter, etc as in Fig 2.4, where:

• ADDR is the position of Macroblock in a frame;

• TYPE is the Macroblock type;

• QUANT is the quantization parameter;

• VECTOR is Motion vector;

• CBP (Coded Block Pattern) show how to split MB into smaller blocks;

• bN is encoded data of residual of color channels (4 Y, 1 Cr, 1 Cb)

Figure 2.4 Macroblock structure

During decompression, the video decoder receives the compressed video data as

a stream of binary data, decodes the elements and extracts the encoded information, including coefficients of variation, size of MB (in bit), motion

prediction information, and so on and perform the reverse transformation to restore the original image data

2.1.3 Motion vector

With H264 compression, frame-based megabytes are predicted based on the information that has been transferred from the encoder to the decoder Usually, there are two ways of predicting frame prediction and inter-frame prediction Frame forecasting uses compressed image data in the same frame as the compressed macroblock and predicts inter-frame image data using previously compressed frames Interframe forecasting is accomplished through a predictive and compensatory motion process in which the motion predator retrieves the macroblock in the reference frame closest to the new macroblock and calculates the motion vector, this vector characterizes the shift of the new macroblock to encoding compared to the reference frame

Referenced macroblocks are sent to the subtractor with the new macroblock that needs coding to find error prediction or residual signal, which will characterize the difference between the predicted macroblock and the actual macroblock The residual signal or prediction error will be converted to Discrete Cosine Transform and quantized to reduce the number of bits to be stored or transmitted These coefficients together with the motion vectors will be applied to the entropy compressor and the bit stream Video streams of binary data include conversion factors, motion prediction information, compressed data structure information, and more To perform video compression, one compares the values of the two frames A frame is used as a reference When we want to compress a MB at

position i of a frame, the video compression algorithm tries to find the reference frame of a MB with the smallest value of MB compared to MB at position i Then,

if MB is found in the reference frame at position j, the change between i and j is called the Motion vector (MV) of MB at position i (Fig 2.5) Normally an MV will consist of two values: x (the column position of MB) and y (row position of

MB)

Figure 2.5 The motion vector of a Macroblock

Note that the MV of a MB does not really describe the motion of the objects in that MB, but merely represents the movement of pixels closest to the pixels in

MB

Proposed method

This section describes the processing of proposored moving object detection method The processing includes three phases: Macroblock-based segmentation, Object-based segmentation, and Object refinement

2.2.1 Process video bitstream

The video data is taken directly from the surveillance camera, in the form of a H264 bitstream Then it is transported to process device To get the MVs and MBs information, I use the library LIVE555 [28] and JM 19.0 [29] LIVE555 is a free, open-source C ++ library that allows to send and receive streams of information through RTP / RTCP, RTSP, and SIP protocols The LIVE555 Streaming Media module is responsible for connecting, authenticating and receiving data from the RTSP stream taken directly from the surveillance camera In addition to receiving packets, LIVE555 Streaming Media also disassembles the header of packets The results from this module are therefore NALUs (refer to ISO/IEC 14496-10 [26]) Then the NALU will be transferred to JM 19.0, a free H264 decode tool commonly used in study and research, for processing The original JM 19.0 input decoder module is a compressed video file with the H264 compression format (with the format described in Annex B of ISO/IEC 14496-10) The original output

is the decompressed video file in YUV format However, in order to reduce the time and volume of computation as originally planned, I made a modification to this library that stopped just extracting the required information without fully decoded the video

Then, the MVs and MBs will be used to detect the moving object I propose a method that uses a combination of both MVs and MBs to determine the motion

in the video This method can be applied to both in-house video and off-road environment Because using the data from compressed domain, it is easy to reduce the processing time of the method compare with the methods use the data in the pixel domain The moving object detection method consists of 3 phases: Macroblock-based segmentation, Object-based segmentation, and Object refinement, as shown in Fig 2.6