scholarly journals Traffic Light and Back-light Recognition using Deep Learning and Image Processing with Raspberry Pi

2021 ◽  
Vol 8 (2) ◽  
pp. 15-19
Author(s):  
Julkar Nine ◽  
Rahul Mathavan
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Real Time ◽  
Network Architecture ◽  
Intelligent Vehicles ◽  
Driving Safety ◽  
Raspberry Pi ◽  
Traffic Light ◽  
Traffic Lights ◽  
Architecture Model

Traffic light detection and back-light recognition are essential research topics in the area of intelligent vehicles because they avoid vehicle collision and provide driver safety. Improved detection and semantic clarity may aid in the prevention of traffic accidents by self-driving cars at crowded junctions, thus improving overall driving safety. Complex traffic situations, on the other hand, make it more difficult for algorithms to identify and recognize objects. The latest state-of-the-art algorithms based on Deep Learning and Computer Vision are successfully addressing the majority of real-time problems for autonomous driving, such as detecting traffic signals, traffic signs, and pedestrians. We propose a combination of deep learning and image processing methods while using the MobileNetSSD (deep neural network architecture) model with transfer learning for real-time detection and identification of traffic lights and back-light. This inference model is obtained from frameworks such as Tensor-Flow and Tensor-Flow Lite which is trained on the COCO data. This study investigates the feasibility of executing object detection on the Raspberry Pi 3B+, a widely used embedded computing board. The algorithm’s performance is measured in terms of frames per second (FPS), accuracy, and inference time.

scholarly journals Traffic Light Controller using Image Processing

2021 ◽  
Vol 12 (2) ◽  
pp. 405-411 ◽  
Author(s):  
Lakshmanan M, Et. al.
Keyword(s):  
Image Processing ◽  
Edge Detection ◽  
Real Time ◽  
Traffic Congestion ◽  
Traffic Signals ◽  
Daily Basis ◽  
Traffic Density ◽  
Traffic Light ◽  
Traffic Lights ◽  
Traffic Systems

Traffic congestion at junctions is a serious issue on a daily basis. The prevailing traffic light controllers are unable to manage the different traffic flows. Most of the current systems operate on a timing mechanism that changes the signal after a particular interval of time. This may cause frustration and result in motorist's time waste. Traffic congestion is a major problem in the currently existing systems. Delays, safety, parking, and environmental problems are the main issues of current traffic systems that emit smoke and contribute to increasing Global Warming. Sensor-based systems reduce the waiting time and maximize the total number of vehicles that can cross an intersection. Our proposed system can control the traffic lights based on image processing without the need for traffic police. This can reduce congestion, delay, road accidents, need for manpower. Under image processing, we use sub techniques like RGB to Gray conversion, Image resizing, Image Enhancement, Edge detection, Image matching, and Timing allocation. A real-time image is captured for every 1 second. After edge detection procedure for both reference and real-time images, these images are compared using SURF Algorithm. Then the amount of traffic is detected and the details are stored in the server. Arduino is used for a traffic signal in the hardware part. It consists of a Wi-Fi module. The micro-controller used in the system Arduino. Four cameras are placed on respective roads and these cameras are used to capture images to analyze traffic density. Then the traffic signals are decided according to the density of traffic. Our technique can be effective to combat traffic on Indian Roads. A lot of time can be saved by deploying this system and also it conserves a lot of resources as well as the economy

scholarly journals Robust Approach to Supervised Deep Neural Network Training for Real-Time Object Classification in Cluttered Indoor Environment

2021 ◽  
Vol 11 (15) ◽  
pp. 7148
Author(s):  
Bedada Endale ◽  
Abera Tullu ◽  
Hayoung Shi ◽  
Beom-Soo Kang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Real Time ◽  
Network Architecture ◽  
Input Data ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Object Classification ◽  
Training Data ◽  
Gradient Descent Algorithm

Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.

scholarly journals A Real Time Image Processing Bird Repellent System Using Raspberry Pi

2020 ◽  
Vol 5 (2) ◽  
Author(s):  
Oluwole Arowolo ◽  
Adefemi A Adekunle ◽  
Joshua A Ade-Omowaye
Keyword(s):  
Image Processing ◽  
Real Time ◽  
Moving Objects ◽  
Detection System ◽  
Local Binary Patterns ◽  
Raspberry Pi ◽  
Feature Identification ◽  
Data Set ◽  
Haar Features ◽  
Haar Feature

Rice is one of the most consumed foods in Nigeria, therefore it’s production should be on the high as to meet the demand for it. Unfortunately, the quantity of rice produced is being affected by pests such as birds on fields and sometimes in storage. Due to the activities of birds, an effective repellent system is required on rice fields. The proposed effective repellent system is made up of hardware components which are the raspberry pi for image processing, the servo motors for rotation of camera for better field of view controlled by Arduino connected to the raspberry pi, a speaker for generating predator sounds to scare birds away and software component consisting of python and Open Cv library for bird feature identification. The model was trained separately using haar features, HOG (Histogram of Oriented Gradients) and LBP (Local Binary Patterns).Haar features resulted in the highest accuracy of 76% while HOG and LBP were, 27% and 72% respectively. Haar trained model was tested with two recorded real time videos with birds, the false positives were fairly low, about 41%. This haar feature trained model can distinguish between birds and other moving objects unlike a motion detection system which detects all moving objects. This proposed system can be improved to have a higher accuracy with a larger data set of positive and negative images. Keywords—Electronic pest repeller Haar cascade classifier, ultrasonic

scholarly journals Lightweight PVIDNet: A Priority Vehicles Detection Network Model Based on Deep Learning for Intelligent Traffic Lights

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6218
Author(s):  
Rodrigo Carvalho Barbosa ◽  
Muhammad Shoaib Ayub ◽  
Renata Lopes Rosa ◽  
Demóstenes Zegarra Rodríguez ◽  
Lunchakorn Wuttisittikulkij
Keyword(s):  
Deep Learning ◽  
Traffic Control ◽  
Detection System ◽  
Lightweight Design ◽  
Vehicle Detection ◽  
Activation Function ◽  
Urban Traffic ◽  
Vehicle Classification ◽  
Traffic Light ◽  
Traffic Lights

Minimizing human intervention in engines, such as traffic lights, through automatic applications and sensors has been the focus of many studies. Thus, Deep Learning (DL) algorithms have been studied for traffic signs and vehicle identification in an urban traffic context. However, there is a lack of priority vehicle classification algorithms with high accuracy, fast processing, and a lightweight solution. For filling those gaps, a vehicle detection system is proposed, which is integrated with an intelligent traffic light. Thus, this work proposes (1) a novel vehicle detection model named Priority Vehicle Image Detection Network (PVIDNet), based on YOLOV3, (2) a lightweight design strategy for the PVIDNet model using an activation function to decrease the execution time of the proposed model, (3) a traffic control algorithm based on the Brazilian Traffic Code, and (4) a database containing Brazilian vehicle images. The effectiveness of the proposed solutions were evaluated using the Simulation of Urban MObility (SUMO) tool. Results show that PVIDNet reached an accuracy higher than 0.95, and the waiting time of priority vehicles was reduced by up to 50%, demonstrating the effectiveness of the proposed solution.

scholarly journals Lightweight Semantic Segmentation Network for Real-Time Weed Mapping Using Unmanned Aerial Vehicles

2020 ◽  
Vol 10 (20) ◽  
pp. 7132 ◽  
Author(s):  
Jizhong Deng ◽  
Zhaoji Zhong ◽  
Huasheng Huang ◽  
Yubin Lan ◽  
Yuxing Han ◽  
...  
Keyword(s):  
Image Processing ◽  
Real Time ◽  
Network Architecture ◽  
Semantic Segmentation ◽  
Real Time Image Processing ◽  
Weed Mapping ◽  
Real Time Image ◽  
Time Gap ◽  
Image Collection ◽  
Time Image

The timely and efficient generation of weed maps is essential for weed control tasks and precise spraying applications. Based on the general concept of site-specific weed management (SSWM), many researchers have used unmanned aerial vehicle (UAV) remote sensing technology to monitor weed distributions, which can provide decision support information for precision spraying. However, image processing is mainly conducted offline, as the time gap between image collection and spraying significantly limits the applications of SSWM. In this study, we conducted real-time image processing onboard a UAV to reduce the time gap between image collection and herbicide treatment. First, we established a hardware environment for real-time image processing that integrates map visualization, flight control, image collection, and real-time image processing onboard a UAV based on secondary development. Second, we exploited the proposed model design to develop a lightweight network architecture for weed mapping tasks. The proposed network architecture was evaluated and compared with mainstream semantic segmentation models. Results demonstrate that the proposed network outperform contemporary networks in terms of efficiency with competitive accuracy. We also conducted optimization during the inference process. Precision calibration was applied to both the desktop and embedded devices and the precision was reduced from FP32 to FP16. Experimental results demonstrate that this precision calibration further improves inference speed while maintaining reasonable accuracy. Our modified network architecture achieved an accuracy of 80.9% on the testing samples and its inference speed was 4.5 fps on a Jetson TX2 module (Nvidia Corporation, Santa Clara, CA, USA), which demonstrates its potential for practical agricultural monitoring and precise spraying applications.

scholarly journals New Solutions Based On Wireless Networks For Dynamic Traffic Lights Management: A Comparison Between IEEE 802.15.4 And Bluetooth

2015 ◽  
Vol 16 (3) ◽  
pp. 224-236 ◽  
Author(s):  
Mario Collotta ◽  
Giovanni Pau
Keyword(s):  
Network Architecture ◽  
Intelligent Transportation System ◽  
Ieee 802.15.4 ◽  
Signalized Intersections ◽  
Traffic Flows ◽  
Traffic Light ◽  
Dynamic Management ◽  
Traffic Lights ◽  
Phase Sequence ◽  
Valid Solution

Abstract The Wireless Sensor Networks are widely used to detect and exchange information and in recent years they have been increasingly involved in Intelligent Transportation System applications, especially in dynamic management of signalized intersections. In fact, the real-time knowledge of information concerning traffic light junctions represents a valid solution to congestion problems. In this paper, a wireless network architecture, based on IEEE 802.15.4 or Bluetooth, in order to monitor vehicular traffic flows near to traffic lights, is introduced. Moreover, an innovative algorithm is proposed in order to determine dynamically green times and phase sequence of traffic lights, based on measured values of traffic flows. Several simulations compare IEEE 802.15.4 and Bluetooth protocols in order to identify the more suitable communication protocol for ITS applications. Furthermore, in order to confirm the validity of the proposed algorithm for the dynamic management of traffic lights, some case studies have been considered and several simulations have been performed.

scholarly journals Real-Time Semantic Segmentation with Dual Encoder and Self-Attention Mechanism for Autonomous Driving

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 8072
Author(s):  
Yu-Bang Chang ◽  
Chieh Tsai ◽  
Chang-Hong Lin ◽  
Poki Chen
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Network Architecture ◽  
Semantic Segmentation ◽  
Autonomous Driving ◽  
Attention Mechanism ◽  
Trade Off ◽  
Segmentation Methods ◽  
General Semantic ◽  
Deep Learning Model

As the techniques of autonomous driving become increasingly valued and universal, real-time semantic segmentation has become very popular and challenging in the field of deep learning and computer vision in recent years. However, in order to apply the deep learning model to edge devices accompanying sensors on vehicles, we need to design a structure that has the best trade-off between accuracy and inference time. In previous works, several methods sacrificed accuracy to obtain a faster inference time, while others aimed to find the best accuracy under the condition of real time. Nevertheless, the accuracies of previous real-time semantic segmentation methods still have a large gap compared to general semantic segmentation methods. As a result, we propose a network architecture based on a dual encoder and a self-attention mechanism. Compared with preceding works, we achieved a 78.6% mIoU with a speed of 39.4 FPS with a 1024 × 2048 resolution on a Cityscapes test submission.

Sign in / Sign up

Export Citation Format

Share Document