Real-time traffic light detection using color density

Tran, Tai Huu-Phuong; Pham, Cuong Cao; Nguyên, Tiên Hiêp; Duong, Tin Trung; Jeon, Jae Wook

doi:10.1109/icce-asia.2016.7804791

Cited by 19 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, an object detection pipeline is built. To do this, two models are used, ssd_inception_v2_coco and faster_rcnn_resnet101_coco [19][20][21][22][23] which are needed to adjust the number of classes (num_classes) to 4 and also set the path for the model checkpoint. The image data sets for training and testing data, and the label map files are created for each class.…”

Section: Training the Modelmentioning

confidence: 99%

Traffic Light Timer Adjustment System Using Threshold Edge Detection for Image Processing: A Software Engineering Approach

Kedwan¹

2023

IJCRM

View full text Add to dashboard Cite

In more enhanced traffic light control, the road traffic in different directions is monitored by sensors and signals. The proposed method presents traffic light control that adapts to traffic density. There are huge number of traffic signaling variables and, therefore, the need for large computing efforts. Thus, the use of electronic sensors is not efficient because it has a high tendency to be affected by noise and it is expensive. The objective of this research project is to develop an integrated traffic light control system based on image processing to calculate the density of the vehicle on the road and set the timer based on the density. Hence, calculating time allocation for each lane based on density. The proposed solution develops a system for controlling the traffic light by image processing using the Threshold Edge Detection (TED) image matching method to identify the density of the traffic. The system will detect vehicles through images, which can then be used for calculating the density of vehicles on road. Cameras mounted on traffic lights will capture image sequences, which are analyzed using digital image processing to detect vehicles. According to road traffic conditions, traffic light timer is adjusted and controlled. Pixel differences are determined (via Pixel-based matching) between the reference image and real time image which is then converted into percentages and based on these percentage difference, different timings can be allotted for controlling the traffic. After TED procedure, both reference and real time images are matched, and traffic lights can be controlled based on difference of percentage in matching.TED Technique is used because it gives better results and higher accuracy as compared to other edge detection techniques when used for detecting vehicles density. It is less sensitive to noise, overcomes the streaking problem, better localization, and accurate edges detection compared to others. Besides, it is cost effective and less prone to error. The proposed solution has a direct effect on reducing the traffic congestion and avoiding the time being wasted by a green light on an empty road. It also helps in directing traffic on different routes without excessive congestion. Hence, provides travel time improvement leading to better driving experience for the community.

show abstract

Section: Training the Modelmentioning

confidence: 99%

Traffic Light Timer Adjustment System Using Threshold Edge Detection for Image Processing: A Software Engineering Approach

Kedwan¹

2023

IJCRM

View full text Add to dashboard Cite

show abstract

“…Therefore, authors converted the RGB color space to other color spaces. HSV color space is used in [14], [15] and [16]. While, [17], [18] and [19] used HSI color space.…”

Section: State Of the Artmentioning

confidence: 99%

Traffic Light Detection: A cost effective approach

Iftikhar,

Riaz,

Ali

et al. 2021

VFAST trans. softw. eng.

View full text Add to dashboard Cite

In last couple of decades, the technological advancements in image and video processing has brought great revolution in our life. Some of the key areas where these advancements have played a key role are: autonomous vehicles, drone technology, crowd monitoring, traffic monitoring, object tracking etc. Nowadays a lot of work is under process for improving capabilities of autonomous vehicles and driver assisted systems. Our focus in this paper is related to automated traffic light detection system with improved capabilities in terms of time complexity and accuracy. The time complexity is directly related to image or video quality with regard to resolution of video and the accuracy is often compromised because of identification of similar objects. The similar objects often appear in video frames when each frame of video is analyzed completely. In order to solve the problem of real time detection of traffic lights in a high-resolution video having 30 frames per second with a resolution of 1280 × 720, we propose an algorithm that systematically searches in middle 70% region of each frame. The proposed algorithm optimizes the search space by dividing middle region into 3. There are three methods for searching and registering a traffic light is proposed in this paper. The basic concept is at single instance a traffic light can exist on one of these three regions. These trategies help in reducing computation complexity tremendously. The Hough Circle Transform technique of image processing is exploited to accurately detect red and green circles of light in the traffic light. Efficacy of the proposed technique in terms of improved time and accuracy is demonstrated on a real dataset collected from Nexar (dashcam mobile solution provider), it encompasses different illumination conditions: day, evening, night, cludy weather and rain etc.

show abstract

“…But these methodologies are also hampered due to the presence of various drawbacks. The systems presented in [1], [4], [7], [8], [10], [11] and [12] fail in considering a vast variety of both Training and Testing datasets, that can be considered to scale the respective systems. [3] and [6] fail on being tested in harsh weather conditions.…”

Section: Behrendt Et Al Have Proposed a Deep Learning Approach Tomentioning

confidence: 99%

Real Time Traffic Light Detection by Autonomous Vehicles using Artificial Neural Network Techniques

Mahesh¹,

T²

2019

IJITEE

View full text Add to dashboard Cite

Autonomous vehicles are the reality of the future, they will open up the way for future advanced systems where computers are expected to take over the decision making of driving. These automobiles are capable of sensing their environment and moving with little or no human input. The main goal of this research is to detect traffic light in real-time for autonomous vehicles. Apart from taking decisions to navigate in the right manner the autonomous vehicles important task is to detect traffic lights, so that it can obey the traffic rules with sufficient precision. The work carried out in this research makes use of two Artificial Intelligence technique, these techniques are compared in accomplishing the task of traffic light detection in real time. The two models that are designed and implemented are Convolution neural network (CNN) and Deep Convolution Inverse Graphics Network (DCIGN). The results clearly show that DCIGN out performance CNN by 8%.

show abstract

Real-time traffic light detection using color density

Cited by 19 publications

References 8 publications

Traffic Light Timer Adjustment System Using Threshold Edge Detection for Image Processing: A Software Engineering Approach

Traffic Light Timer Adjustment System Using Threshold Edge Detection for Image Processing: A Software Engineering Approach

Traffic Light Detection: A cost effective approach

Real Time Traffic Light Detection by Autonomous Vehicles using Artificial Neural Network Techniques

Contact Info

Product

Resources

About