MINISTRY OF EDUCATION AND TRAINING HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION GRADUATION PROJECT AUTOMOTIVE ENGINEERING DESIGN START STOP CIRCUIT THROUGH TRAFFIC DETECTION LECTURER: Assoc.Prof DO VAN DUNG STUDENT: LE CHAN PHAM VO HUY VU SKL 010586 Ho Chi Minh City, December 2022 HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION FACULTY FOR HIGH QUALITY TRAINING GRADUATION PROJECT DESIGN START STOP CIRCUIT THROUGH TRAFFIC DETECTION Students: Le Chan Pham ID: 18145045 Vo Huy Vu ID: 18145080 Major: AUTOMOTIVE ENGINEERING Advisor: Assoc.Prof Do Van Dung Ho Chi Minh City, 24 December 2022 HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION FACULTY FOR HIGH QUALITY TRAINING GRADUATION PROJECT DESIGN START STOP CIRCUIT THROUGH TRAFFIC DETECTION Students: Le Chan Pham ID: 18145045 Vo Huy Vu ID: 18145080 Major: AUTOMOTIVE ENGINEERING Advisor: Assoc.Prof Do Van Dung Ho Chi Minh City, 24 December 2022 THE SOCIALIST REPUBLIC OF VIETNAM Independence – Freedom– Happiness -------- Ho Chi Minh City, December, 2022 GRADUATION PROJECT ASSIGNMENT Student name: LE CHAN PHAM Student ID: 18145018 Student name: VO HUY VU Student ID: 18145030 Major: Automotive engineering technology Advisor: Assoc.Prof DO VAN DUNG Phone number: 0966879932 Date of assignment: Octorber 2022 Date of submission: December 2022 1. Project title: Design Start Stop circuit through object detection 2. Equipment: Laptop with GPU, HD Camera, Arduino UNO 3. Content of the project: Research convolutional neural networks, YOLO algorithm model, train YOLO model, evaluate the results and use output to control Arduino.
Final product: Traffic light detection system through webcam, videos and images CHAIR OF THE PROGRAM ADVISOR Sign with full name Sign with full name THE SOCIALIST REPUBLIC OF VIETNAM Independence – Freedom– Happiness -------- Ho Chi Minh City, December, 2022 ADVISOR’S EVALUATION SHEET Student name: LE CHAN PHAM Student ID: 18145045 Student name: VO HUY VU Student ID: 18145080 Major: Automotive engineering technology Project title: Design Start Stop circuit through object detection EVALUATION 1. Content of the project:. Approval for oral defense? (Approved or denied) .) Ho Chi Minh City, …. day, … year ADVISOR (Sign with full name) 2 THE SOCIALIST REPUBLIC OF VIETNAM Independence – Freedom– Happiness -------- Ho Chi Minh City, December, 2022 PRE-DEFENSE EVALUATION SHEET Student name: LE CHAN PHAM Student ID: 18145045 Student name: VO HUY VU Student ID: 18145080 Major: Automotive engineering technology Project title: Design Start Stop circuit through object detection Name of Reviewer: …………………………………………………………………… EVALUATION 1.
Content of the project:. Approval for oral defense? (Approved or denied) .) Ho Chi Minh City, …. day, … year REVIEWER (Sign with full name) 3 THE SOCIALIST REPUBLIC OF VIETNAM Independence – Freedom– Happiness -------- Ho Chi Minh City, December, 2022 EVALUATION SHEET OF DEFENSE COMMITTEE MEMBER Student name: LE CHAN PHAM Student ID: 18145045 Student name: VO HUY VU Student ID: 18145080 Major: Automotive engineering technology Project title: Design Start Stop circuit through object detection Name of Defense Committee Member: ………………………………………………… EVALUATION 1. Content of the project:.
Approval for oral defense? (Approved or denied) .) Ho Chi Minh City, …. day, … year COMMITTEE MEMBER (Sign with full name) DISCLAIMER The authors, Le Chan Pham and Vo Huy Vu confirm that the work presented in this thesis is ours. All the data and statistics in the thesis are reliable and are not published in any previous studies or research. Where information has been derived from other sources, we confirm that this has been indicated in the thesis.
i ACKNOWLEDGE Throughout our studies and graduation process, my team was always cared for, guided, and assisted by teachers from the Faculty of High Quality Training, as well as the support and assistance from friends and colleagues. First and foremost, we want to thanks The Board of Directors of Ho Chi Minh City University of Technology and Education for creating all conditions in terms of facilities along with modern equipment and library system with a variety of documents, which is convenient for students in order to research information. We would like to express our gratitude to the instructor Assoc.Prof Do Van Dung for assisting and leading us in complete this project. Because of the team’s limited experience, this study will have errors when practicing and finishing the graduation thesis.
We are looking forward to hearing feedback and advice from professors to help us complete our report. Sincerely thank you! Ho Chi Minh City, 24th December 2022 ii CONTENTS DISCLAIMER. xii CHAPTER 1: INTRODUCTION. Reason for choosing topic:.
Scope of research:. Overview of traffic lights system:. Overview of Engine Start Stop system:. How does engine start stop system work?.
What are the benefits of Stop-Start?. What are the downsides of Stop-Start?. Introduction to Deep Learning:. What is Deep Learning:.
The difference between the Machine Learning and Deep Learning :. Some neural network in Deep Learning:. Overview of Convolutional Neural Network in image classification:. What is Convolutional Neural Network?.
Convolutional Neural Network Architecture:. How to detect an object:. Introduction some object detection algorithm: .30 CHAPTER 3: YOLO ALGORITHM MODEL. What is YOLO?.
YOLO algorithm model:. Prediction output in YOLO:. Multi-label image classification:. Non-maximum suppression (NMS):.
Intersection Over Union (IOU):. YOLO network architecture:. Mean Average Precision (mAP): .79 CHAPTER 4: DESIGN IDEAL ENGINE START-STOP SYSTEM MODEL AND ALTERNATIVE ENGINE START-STOP SYSTEM MODEL. Design ideal engine start-stop system model: .1 Changes in the classic engine start-stop system model : .2 Components of the ideal engine start-stop system model:.3 Process of the ideal engine start-stop system model: .2 Alternative engine start-stop system model:.
RESULT AND FUTURE DEVELOPMENT .1 Label image for training:.2 Training Yolo on Google Colab: .3 Operate Yolo on Windows:. Connect Arduino to Python: .115 v LIST OF FIGURES AND TABLES Figure 2. Diagram of the engine start stop circuit. Engine Start Stop button on Mercedes.
Comparison between Machine Learning and Deep Learning. The typical structure of ANN. A looping constraint on the hidden layer of ANN turns to RNN. Operation example of RNN.
Output of Convolution. CNN – Image Classification. Comparing the different between ANN, RNN, CNN. Layers in a CNN network.
CNN network model – AlexNet. The image that the computer sees. Convolution between input and a kernel to generate data for a hidden layer neuron. Example of a convolutional layer.
Graph of Sigmoid function. Graph of ReLU. Graph of Leaky ReLU function. Example of pooling layer.
Fully-Connected Layer. The relationship between network depth and performance. Residual Block model. Object detection in computer vision.
Image processing diagram. Faster R-CNN model. YOLO input image is divided into 7 ×7. Example of calculating boundary box coordinates in 448× 448 size.
Output of YOLOv3. Output of YOLOv3. Anchor box solves the problem of detecting many objects that appear on the same output image area. Example of multi-object recognition (person and vehicle) appearing in the same area.
YOLOv3 can detect objects with similar characteristics such as women and people. Ratio between area of overlap and area of unio. General architecture of YOLO. How the classification loss function work.
Formula to estimate boundary box from anchor box. MS COCO object detection. An object detection mode. Dense block layers.
Cross-stage-partical-connection. Object detection process. Applying SPP in Yolo( without DC block). Yolo with SPP (with DC block).
Path Aggregation Network (PAN). The design of Neck. In yolov4, the researchers changed add function to contact function. In yolo4, the researchers changed add function to contact function.
Spatial Attention Module. Convolutional Block Attention Module. CutMix data augmentation. Mosaic data augmentation.
Class label smoothing. Output landscape for Mish comparison. Multi-input weighted residual connections. Deepwise Conv block.
Invert Residual Block. Net layer in the cfg file. It should be noted that the [yolo] layers and [convolution] layers are configured before [yolo] when you want to detect selected objects. Illustration of TP and FP.
Classic Engine Start-Stop system. Ideal Engine Start-Stop system. NVIDIA Jetson Nano A02. What's on NVIDIA Jetson Nano.
Battery VARTA AGM LN6 605901053 12V 105AH. Ideal Start-Stop system work flow. Alternative Start=Stop work flow. Laptop Dell G3 Gaming with NVIDIA GTX 1050 Ti GPU.
Training data folder. Predefined-classes file. A file label of an image. Clone Yolov7 from Github .Install necessary library.
Try to detect with pretrain weight. Unzip training data from Drive. Reorganize the training data folder. Start to train YOLO.
Try to detect after training and print out result. Open Yolo path and import library. Start detect model by run detect. Detect in real-time with image on mobile phone.
Upload example to Arduino. Connect Arduino to Python. Logic code for connecting arduino. Detect image on the internet.
Detect an image on the internet. Detect object small and far away. Detect in low bright condition. Detect with flared condition.
Detect video with obstacle. Detect in real time. 112 x LIST OF ABBREVIATIONS AI: Artificial Intelligence CNN: Convolutional Neural Network RNN: Recurrent Neural Network ANN: Artificial Neural Network IoT: Internet of Things ResNet: Residual Neural Network R-CNN: Region-based Convolutional Neural Network Fast R-CNN: Fast Region-based Convolutional Neural Network Faster R-CNN: Faster Region-based Convolutional Neural Network SSD: Single Shot Multi-box Detector YOLO: You Only Look Once MAP: Mean Average Precision IOU: Intersection Over Union GPU: Graphics Processing Unit CPU: Central Processing Unit DNN: Deep Neural Network CUDA: Compute Unified Device Architecture CuDNN: NVidia CUDA® Deep Neural Network ReLU: Rectified Linear Unit RoI: Region of Interest FPS: Frame Per Second xi ABSTRACT The world is witnessing a rapid change in the future of artificial intelligence. Automobile brands are investing millions of dollars in developing information technology.
Thanks to object detection, we can manufacture many different automatic systems. Because of that, we decide to improve the traditional engine start stop system efficiency by adding the traffic light detection system. Firstly, we must learn about the object detection algorithm. We also know about the engine start stop system working principle and its electric circuit.
In this project, we develop an object detection model base on YoloV7 model and use Python language in operation. xii CHAPTER 1: INTRODUCTION 1. Reason for choosing topic: Traditional engine start-stop technology’s working principle is that the engine stops once the brake pedal has been depressed for 2 seconds, and runs again when the brake pedal is depressed again, which helps save energy. However, this trigger technology has two important disadvantages: − When a vehicle stops for red light for less than 5 seconds, the fuel consumed by activating the engine start-stop technology is more than when the engine idles for a time for the red light.
− It only considers the vehicle status, stopping or running, but neglects the road status, especially road congestion, which leads to frequent start-stop activation, further affecting both vehicle stability driving comfort. The main reason for the above disadvantages is the unintelligent engine start-stop system trigger. To solve this problem, this project combines the traditional engine start-stop system with traffic lights detection using Yolo algorithm model. System can effectively improve the driving experience, reduce engine fuel consumption, and help promote traditional engine start-stop technology.
In recent years, the wave of artificial intelligence is exploding strongly and its application are endless. The technology and AI application can be applied in many fields such as healthcare, self-driving cars, smart home, social media, space exploration,… However, the application of AI in real world requires not only high accuracy but also fast response speed. In object detection, there are many advanced models born to solve this problem, but most of them cannot be used in real time due to large computational resource requirements.