Robust Nighttime Vehicle Detection by Tracking and Grouping Headlights

Zou, Qi; Ling, Haibin; Luo, Siwei; Huang, Yaping; Mao, Tian

doi:10.1109/tits.2015.2425229

Cited by 35 publications

(18 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional vision-based vehicle detection methods can be divided into two categories: the appearance-based method or the motion-based method. The appearance-based methods use shadow feature [10], symmetry property [11], color [12], texture [13], and headlights/taillights [14,15] to detect vehicle. Also, some methods introduce machine learning classifiers to train appearance features.…”

Section: Introductionmentioning

confidence: 99%

Vehicle Detection and Ranging Using Two Different Focal Length Cameras

Liu

Zhang

2020

Journal of Sensors

View full text Add to dashboard Cite

Vehicle detection is a crucial task for autonomous driving and demands high accuracy and real-time speed. Considering that the current deep learning object detection model size is too large to be deployed on the vehicle, this paper introduces the lightweight network to modify the feature extraction layer of YOLOv3 and improve the remaining convolution structure, and the improved Lightweight YOLO network reduces the number of network parameters to a quarter. Then, the license plate is detected to calculate the actual vehicle width and the distance between the vehicles is estimated by the width. This paper proposes a detection and ranging fusion method based on two different focal length cameras to solve the problem of difficult detection and low accuracy caused by a small license plate when the distance is far away. The experimental results show that the average precision and recall of the Lightweight YOLO trained on the self-built dataset is 4.43% and 3.54% lower than YOLOv3, respectively, but the computing speed of the network decreases 49 ms per frame. The road experiments in different scenes also show that the long and short focal length camera fusion ranging method dramatically improves the accuracy and stability of ranging. The mean error of ranging results is less than 4%, and the range of stable ranging can reach 100 m. The proposed method can realize real-time vehicle detection and ranging on the on-board embedded platform Jetson Xavier, which satisfies the requirements of automatic driving environment perception.

show abstract

Section: Introductionmentioning

confidence: 99%

Vehicle Detection and Ranging Using Two Different Focal Length Cameras

Liu

Zhang

2020

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…Some more robust vehicle detection and tracking methods, e.g. [21]- [24], can be used in the future to handle more complicated situations, e.g. in heavy raining or foggy conditions, (when more processing power becomes available).…”

Section: Resultsmentioning

confidence: 99%

Machine Vision to Alert Roadside Personnel of Night Traffic Threats

Wang

Horn

2018

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

In the United States, every year, several people whose job takes them to the sides of roads, are injured or killed by roadside collisions. This could be avoided if a warning signal could be sent to them. In this paper, we describe a machinevision based alerting system which detects and tracks headlamps of cars in night traffic. The system automatically computes a "normal traffic" region in the image. Unusual trajectories of cars are detected when the images of their headlamps move out of that region. The system promptly sends a warning signal once a risk has been identified. The system runs on the Android smart phones, which are mounted on cars or on roadside fixtures.

show abstract

“…When the degree of illumination is poor, such as under rainy and dusky conditions, the performance may be affected. The method in [15] trained AdaBoost classifier for headlight detection in order to reduce the false detection raised by reflections; headlight pairing was also conducted, and then the paired headlights were tracked. This method was heavily relyiant on detection results of vehicles' headlights.…”

Section: Related Workmentioning

confidence: 99%

A Deep-Learning-Based Vehicle Detection Approach for Insufficient and Nighttime Illumination Conditions

Leung

Chen

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

Most object detection models cannot achieve satisfactory performance under nighttime and other insufficient illumination conditions, which may be due to the collection of data sets and typical labeling conventions. Public data sets collected for object detection are usually photographed with sufficient ambient lighting. However, their labeling conventions typically focus on clear objects and ignore blurry and occluded objects. Consequently, the detection performance levels of traditional vehicle detection techniques are limited in nighttime environments without sufficient illumination. When objects occupy a small number of pixels and the existence of crucial features is infrequent, traditional convolutional neural networks (CNNs) may suffer from serious information loss due to the fixed number of convolutional operations. This study presents solutions for data collection and the labeling convention of nighttime data to handle various types of situations, including in-vehicle detection. Moreover, the study proposes a specifically optimized system based on the Faster region-based CNN model. The system has a processing speed of 16 frames per second for 500 × 375-pixel images, and it achieved a mean average precision (mAP) of 0.8497 in our validation segment involving urban nighttime and extremely inadequate lighting conditions. The experimental results demonstrated that our proposed methods can achieve high detection performance in various nighttime environments, such as urban nighttime conditions with insufficient illumination, and extremely dark conditions with nearly no lighting. The proposed system outperforms original methods that have an mAP value of approximately 0.2.

show abstract

Robust Nighttime Vehicle Detection by Tracking and Grouping Headlights

Cited by 35 publications

References 18 publications

Vehicle Detection and Ranging Using Two Different Focal Length Cameras

Vehicle Detection and Ranging Using Two Different Focal Length Cameras

Machine Vision to Alert Roadside Personnel of Night Traffic Threats

A Deep-Learning-Based Vehicle Detection Approach for Insufficient and Nighttime Illumination Conditions

Contact Info

Product

Resources

About