Long-Distance Vehicle Dynamic Detection and Positioning Based on Gm-APD Lidar and LIDAR-YOLO

Ding, Yuanxue; Qu, Yingdong; Du, Dakuan; Jiang, Yanze; Zhang, Hailong; Song, Boyi; Zhou, Xin; Sun, Jianfeng

doi:10.1109/jsen.2022.3193740

Cited by 13 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method includes license plate detection, digit segmentation, and distance estimation modules. Experimental results demonstrate improved performance compared to previous methods, particularly for shorter distances up to 10m.In a modified version of YOLOv3 [3], the loss function responsible for absolute distance estimation is adjusted, and the training data is modified accordingly. By utilizing the KITTI dataset for benchmarking, the researchers achieved promising results, with mean absolute distance error of 2.5m and mean relative error of 11%.…”

Section: Related Workmentioning

confidence: 99%

Rear End Object Detection and Alarm System for Intelligent Transportation

2023

INDJCSE

View full text Add to dashboard Cite

With the rapid development of the economy, vehicles have become the primary mode of transportation in people's daily lives. Among the various types of car accidents, rear-end collisions are quite common. Installing a rear-facing camera on the back of a vehicle can provide valuable assistance to drivers, including collision warning systems. By incorporating rear-end detection, drivers no longer need to look behind them. This system can detect objects on the road when the car is traveling at speeds over 80 km/h on a highway. Once activated, the system pre-processes the camera image to identify objects within it. If another vehicle is less than ten feet away and traveling in the same lane, a beep will sound. This is achieved by determining the lane the vehicle is in, estimating the object's distance from the camera, and utilizing the YOLOv5 object detection algorithm. To address the issue of the YOLOv5 vehicle detection algorithm missing detections for small and dense objects in complicated situations, the YOLOv5 vehicle detection method has been developed. The third-order B-spline curve model and the canny edge detection method were employed to fit the lane lines. This method has strong flexibility and resilience, and can describe lane lines of various shapes. The distance can be approximated by considering the labeled region found in the video. An alarm will sound to alert the driver if the distance is less than 3 meters. This technology will eliminate the vehicle's rear blind spot, ensuring the driver's safety.

show abstract

Section: Related Workmentioning

confidence: 99%

Rear End Object Detection and Alarm System for Intelligent Transportation

2023

INDJCSE

View full text Add to dashboard Cite

show abstract

“…Vehicle detection technology in semantic Web-based video surveillance systems can provide strong decision support for managers. Compared to other detection technologies (Zhao et al, 2022;Ding et al, 2022;, semantic Web-based video surveillance has several advantages, including convenient installation and maintenance, no need to interrupt traffic, low cost, large amounts of analyzable information, and no impact on road life. Currently, this technology is experiencing rapid development (Tsai & Chen, 2021;Mo et al, 2022;.…”

Section: Introductionmentioning

confidence: 99%

MC-YOLO-Based Lightweight Detection Method for Nighttime Vehicle Images in a Semantic Web-Based Video Surveillance System

Wang,

Hao,

Wang

2023

International Journal on Semantic Web and Information Systems

View full text Add to dashboard Cite

Semantic web-based video surveillance systems can provide strong decision-making support for managers, and they have high requirements for real-time and precision of vehicle detection models in complex night scenes. To address this issue, a lightweight nighttime vehicle detection method (MC-YOLO) integrating MobileNetV2 and YOLOV3 is proposed. Firstly, in the preprocessing stage, image enhancement is performed on nighttime images to facilitate model feature extraction. Then, the lightweight network MobileNetV2 is used to extract feature by replacing the backbone network DarkNet53 in YOLOv3, thus accelerating the speed of target detection. Finally, after the convolution operation of the backbone network, a convolution block attention module is added to enhance the important feature information and suppress the secondary features, thereby improving the detection precision. The experimental results on the BDD100K dataset show that the proposed MC-YOLO model has a precision of up to 92.75%, which is superior to several other advanced comparative models.

show abstract

“…These methods can get high scores in mean average precision (mAP) proposed in Microsoft COCO, which is the most widely used metric in object detection. Some improved detection frameworks have been conducted into industry areas like indoor scenes [4] and vehicle detection [5]. Generally, most of the detectors under specific scenes are born from the representative detectors, including the R-CNN series [6], [7] and the one-stage series such as YOLO [2].…”

Section: Introductionmentioning

confidence: 99%

RGB-W based Hazard Detection in Electric Power Communication Networks

2023

Proceedings of 2023 the 13th International Workshop on Computer Science and Engineering

View full text Add to dashboard Cite

Hazard detection is an important computer vision area in electric power communication network.In this paper, we propose a hazard detection method in electric power communication network. This method turns the short-range wireless localization information into a confidence mask corresponding to the image size. The mask is able to be input into object detectors to revise confidence scores. The proposed method aims to increase the accuracy of the detections and alleviate the problems of false positives and false negatives. We design two kinds of confidence mask in order to find a better method to utilize the localization information. In addition, dataset containing specific scenes is collected to train and test the proposed method of hazard detection task in electric power communication network. Finally, this paper adopts various metrics to evaluate the effectiveness of the proposed method. The experiments demonstrate the feasibility and superiority of the proposed method in both theory and practice.

show abstract

Long-Distance Vehicle Dynamic Detection and Positioning Based on Gm-APD Lidar and LIDAR-YOLO

Cited by 13 publications

References 41 publications

Rear End Object Detection and Alarm System for Intelligent Transportation

Rear End Object Detection and Alarm System for Intelligent Transportation

MC-YOLO-Based Lightweight Detection Method for Nighttime Vehicle Images in a Semantic Web-Based Video Surveillance System

RGB-W based Hazard Detection in Electric Power Communication Networks

Contact Info

Product

Resources

About