VIETNAM NATIONAL UNIVERSITY - HO CHI MINH CITY UNIVERSITY OF INFORMATION TECHNOLOGY FACULTY OF INFORMATION SYSTEMS LE TRAN BAO NAM DINH XUAN HUNG GRADUATION THESIS A STOLEN VEHICLE LOCATOR SYSTEM VIA DASHCAM BACHELOR OF ENGINEERING IN INFORMATION SYSTEMS HO CHI MINH, 2022 VIETNAM NATIONAL UNIVERSITY - HO CHI MINH CITY UNIVERSITY OF INFORMATION TECHNOLOGY FACULTY OF INFORMATION SYSTEMS LE TRAN BAO NAM- 18521123 DINH XUAN HUNG- 18520791 GRADUATION THESIS A STOLEN VEHICLE LOCATOR SYSTEM VIA DASHCAM BACHELOR OF ENGINEERING IN INFORMATION SYSTEMS INSTRUCTOR Ph. NGUYEN THANH BINH HO CHI MINH, 2022 INFORMATION ON THE THESIS GRADUATION GRADING COUNCIL Graduation thesis grading council, established under Decision No. of the Principle of the University of Information Technology. ACKNOWLEDGMENT Finally, I would like to express my sincerest thanks for my Ph.
Nguyen Thanh Binh enthusiastically guided and supported us throughout the study and research process to complete the thesis. In addition to teaching and commenting on academic knowledge, presentation skills, research, and reporting, he also cares about students’ health and psychology, as well as always listens, shares, and inspires students and motivated us to complete the thesis. The knowledge and skills imparted by him will definitely be valuable luggage for our future growth. Next, we would like to thank the Information Systems Laboratory for facilitating and supporting us during the course of the graduation thesis.
Besides, we would also like to thank the teachers in the Faculty of Information Systems in particular, and the teachers in the University of Information Technology - Vietnam National University, Ho Chi Minh City in general, for teaching us knowledge and skills for us during the past four years of school. Once again, I would like to express my gratitude to Ph. Nguyen Thanh Binh and the teachers who have always accompanied and supported me during my university studies. Le Tran Bao Nam Dinh Xuan Hung TABLE OF CONTENTS Chapter 1.
BACKGROUND KNOWLEDGE AND CURRENT WORKS. Automatic License Plate Recognition Approaches. License Plate Detection. Edge-Based Methods.
Color-Based Methods. Texture-Based Methods. Character-Based Methods. Deep-Learning Techniques.
License Plate ReCOgMition. Pre-Processing Techniques. OUR PROPOSED LICENSE PLATE RECOGNITION APPROACH. General Processing Flow.
Annotation Tool and Dataset. Solution for License Plate RecognitiON. License Plate Recognition Processing Flow. Model SeπCtiOT.
+ + kh HT TH HH TH HH 39 3. + + 5+ + HH HH TT 44 3. Evaluation and COIIDATISOH. - 5% xxx ket ghe 57 3.
Dataset Evaluating of Object Detection and Object Recognition. APPLICATION DESIGN AND IMPLEMENTATION. System ATChIf€CfUTC. ¿5c c1 121 1 1 11121211111 HH HH TH HH 68 4.
Implement Sy§Sf€Im. + + E11 E11 1 E11 HH HH HT Hi 70 4.--- - - ¿25+ 2% S*SE2E£E#EEEk2kEkrkrkrkerrrrrkrrerrree 73 CS.-- + tt Ỳ HH He. RESULTS AND CONCLUSIONS.--- -- - 6 <1 12k ST HH Hi 85 5. 88 TABLE OF FIGURES Figure |.
Main stages in a multi-stage license plate recognition system [6]. Classification of related license plate detection techniques [6]. License plate recognition pipeline with associated techniques [6]. Flowchart diagram of the Automation License Plate Recognition process [2] —.
General processing ÍÏOW. Roboflow license plate detection dataset OV€TVICW. Roboflow license plate detection training dataset. Roboflow license plate detection validation dataset.
Roboflow license plate detection testing dafaSet. Roboflow license plate recognition dataset OVeTVIeW. Roboflow license plate recognition training dataset oo. Roboflow license plate recognition validation daf(aset.
Roboflow license plate recognition testing dataset. Our license plate detection dataset. ¿+ S5 S*9E£E£E£EEEEEEEkEEEEEEkEEEkEEEETH tr, 37 Figure 16. Label file after labeled.
License Plate Recognition Processing FÏOW. ---cc«ccxsxsserrrexex 38 Figure 18. Object detection using YOLO [56]. YOLOvS5 Network architecture [61].
A comparative plot of the performance of the YOLOvS family [57] Figure 21. Network architecture of VGG16-SSD. Network architecture of SSD-MobileNet [63] .zip folder structure. Install YOLOv5 dependencies.
Create configuration file. Convert model to TF Lite and quantization it. Result from the quantization model.------ 2+ 2+5 +£+z++++£+se++zsz++ 48 Figure 29.zip folders S†TUCfUTG. Install Tensorflow object detection dependencies.
Create Labelmap and TFReCOrd. Pipeline configuration of SSD MobileNetW2. Convert model to Tensorflow Imodel. Convert Tensorflow model to Tensorflow Lite model.
Get list of all images in train fOÏder. Convert to Tensorflow Lite model with representative images. Result of YOLOv5 quantization model.------ - + scs+++s+c+<e+szsz++ 57 Figure 40. Dataset evaluating of license plate detection and license plate recognition.
Frame1000 License Plate Detection Evaluating with SSD MobileNet V2. Frame1000 License Plate Detection Evaluating with YOLOVS. Frame382 License Plate Recognition with SSD MobileNet V2. Frame382 License Plate Recognition with YOLOV5.
Frame382 License Plate Recognition with SSD MobileNet V2 for both license plate detection and license plate recOgnitiON.--¿--- 5-52 255+++s+c+ss+sz<cs+ 64 Figure 46. Frame382 License Plate Recognition with SSD MobileNet V2 for license plate detection and YOLOVS for license plate recognition. Frame382 License Plate Recognition with YOLOvS for license plate detection and SSD MobileNet V2 for license plate recognifiOn. Frame382 License Plate Recognition with YOLOvS for both license plate detection and license plate recognition 65 Figure 49.
Client Login Page. Client Profile Page. Client Home Page. Client List Camera Page.
Client Create New CaIm€Ta. - - + th vn nh ve 72 Figure 62. Client Lost Vehicle List Page. Client Request Lost Vehicle Page.
Admin Login Page. Admin Profile PPage. Users Management Page. Lost Vehicles Management Page.
Lost Vehicle Request Page .----- -- ¿+2 25222 St2t2Etersrrkrterrrrrrree 75 Figure 70. Cameras Management Page. Admin Create New Camera Page .--¿-¿- 5c + Stt‡kéEkEEEkekererrkekrke 76 Figure 74. API DoCUIN€HL.
ERD diagram of Stolen lost vehicle locator system. Dashcam haT(ÌWATC. - - S1 EE121 1E 131 1012111 111 H0 HH HH ii 84 Figure 78. User login into system oo.
ccc escesesesesssseescseseeesesesessesessseersesneaeseensessseaees 85 Figure 79. Home page after user logged into system. User create a new lost vehicle request. User's list of lost vehicles .--- - ¿+55 SS+‡EEEEk+kEEEEEEkrkekerrkrkerke 86 Figure 82.
Lost vehicle's location showed on a map on the home page. 87 LIST TABLES Table 1. Comparison speed inference between models on Raspberry Pi for license plate CeteCtiON ĐT 4134. Comparison speed inference between models on Raspberry Pi for license plate detection and license plate T€COØTIẨIOTI.- - 5 s1 931991193 91 9119 1 2v vn rệt 59 Table 3.
Mean average precision comparison of license plate detection. Mean average precision comparison of license plate recoønition. - 6 5 2E 1625191018511 11 911 11 91 210 H1 hi HH nh nh nh rg 66 Table 6. Table of TOÏ€.
26 c1 2319911231 1131191 931 1 vn HH TH HH HH rc 80 Table 8. Table Camera Detected ResulÏ(. Table of lost vehicle reQU€SES. Current Situation In the complicated situation of the Covid-19 epidemic, crimes of property rights infringement tend to increase, mainly "Theft of property" and of which the majority is theft motorcycle.
According to the statistics of the City Police. In Ha Noi City, for every 10 cases of property theft, there will be 4 cases of motorbike theft with the rate of 40% [1] and the rate of investigation to find a stolen vehicle is very low, less than 30% [2]. This type of crime tends to increase in part due to the complicated and prolonged epidemic situation, which leads many businesses to suspend operations, many people to lose their jobs, and fall into economic difficulties. However, the epidemic is not the only cause of the increase in this type of crime.
Many subjects are lazy to work, have good conditions, have the ability to find jobs, work on their own to generate income to serve themselves and their families, but with a sense of being lazy to work, preferring to enjoy the results. other people's labor but commit acts of stealthily appropriating other people's property. Considering the consequences caused by property theft, it can be seen that: all acts of infringing upon the property of others need to be detected and dealt with strictly to limit the impact on social order and security. as well as the anxiety of the people.
Current Solution To prevent motorbike theft effectively, the most important thing is the awareness of each person in protecting their own property. And currently, the safest solution to this problem is still attaching a locator to a vehicle with a relatively high cost (1,100,000 VND — 1,800,000 VND for | motorcycle locator including: GPS, SIM locator device. Data 4G 1-year package attached to the device, 1-year free monitoring management software, on- site installation by workers). Moreover, currently, in Ho Chi Minh City's districts, robbery hunting teams have also been established to assist people in finding stolen vehicles, but most of these teams are based on vehicle search operations on the locator mounted on the vehicle, but for the vehicles without the locator, the search is almost impossible.
e Report stolen vehicle at police stations o Advantages: Official solution of the Ministry of Public Security of Vietnam with the highest reliability in the solutions. o Disadvantages: The process of reporting and finding stolen vehicles is complicated and time-consuming. e Attaching a locator to a vehicle o Advantages: Real-time vehicle tracking. o Disadvantages: High cost, battery of motorbike are easily damaged.
e Report stolen vehicle to robbery hunting teams o Advantages: The process of reporting and finding stolen vehicles is done quickly. o Disadvantages: Short finding period, depends mainly on locator attached on vehicle. Our Solution Decree No. 10/2020/ND-CP stipulates that passenger transport business vehicles of 9 seats or more, containerized freight vehicles, and tractors must have cameras that store images during the journey [3].
According to data reported by the Directorate for Roads of Vietnam and the Department of Transport, by the end of December 31, 2021, the percentage of active transport business vehicles with cameras installed reached more than 81% (103,000). vehicles out of a total of 126,000 vehicles). In which, passenger cars with 9 seats or more reached 100%, fixed route passenger cars 91%, contract cars 69%, container trucks 82% and tractors 78% [3]. Car dashcam market research report on Shopee, Tiki, and Lazada e-commerce platforms for sellers from January 2022 to December 2022, conducted by Metric.vn, shows the revenue of dashcams transactions on the e-commerce platform reached VND 3 billion in 12 months and increased by more than 89.8% compared to the last quarter [4].
Through the above research data, to solve the problem of motorcycle theft, our team proposes the solution "A Stolen Vehicle Locator System Via Dashcam". e Advantages: o Real-time notification of stolen vehicle location after being detected by dash cam. o Easy to use system. o Can be easily integrated with existing modules and solutions.
o The process of reporting and finding stolen vehicles is done quickly. e Disadvantages: o Dashcam owners privacy issues. o The success rate of finding a stolen vehicle depends on the number of cameras in the network. o Trade-off between precision and speed in license plate detection.
o Existing dashcam can not be combined with our module. Objectives e Build a complete system that responds to the described process. e The stolen vehicle image and location will be stored on the cloud and users can access the information on the Web platform. e Fast speed of license plate extraction, high accuracy, intuitive Web interface, easy for users to get used to and use.
® Deploy network architecture YOLOv5 and SSD MobileNetV2 on embedded computer. e Testing, evaluating, and comparing two different detection models are SSD MobileNetV2 and YOLOVS to choose the right model. Scope e Building license plate dataset in Vietnam in general and Ho Chi Minh City in particular. e Using YOLOv5 and Single Shot Detection in license plate recognition.
BACKGROUND KNOWLEDGE AND CURRENT WORKS 2. Automatic License Plate Recognition Approaches According to the solution mentioned in Chapter 1, the identification of a stolen vehicle depends on the dashcam recognizing the license plate of the vehicle moving on the road and then sending the information back to the system. Therefore, license plate recognition is an important key to the solution.