Incorporating appearance and edge features for vehicle detection in the blind-spot area

Lin, Bin-Feng; Chan, Yi-Ming; Fu, Li‐Chen; Hsiao, Pei‐Yung; Chuang, Li-An; Huang, Shih-Shinh

doi:10.1109/itsc.2010.5625221

Cited by 10 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the Section 3.2.1, nonredundant object and background samples can be obtained. There are two cases needed to be considered: (1) The object samples obtained in the frame is less than 2, which will lead to the result that the D i,j in Eq. ( 5) cannot be calculated.…”

Section: Network Trainingmentioning

confidence: 99%

See 1 more Smart Citation

Distorted Vehicle Detection and Distance Estimation by Metric Learning-Based SSD

Zhang¹,

Jin²,

Kan³

et al. 2021

IJCIS

View full text Add to dashboard Cite

Object detection and distance estimation based on videos are important issues in advanced driver-sssistant system (ADAS). In practice, fisheye cameras are widely used to capture images with a large field of view, which will produce distorted image frames. But most of the object detection algorithms were designed for the nonfisheye camera videos without distortion, which is not suitable for the application of ADAS since one always expects the panorama stitching and object detection system should share one set of cameras. The research of vehicle detection based on fisheye cameras is relatively rare. In this paper, vehicle detection and distance estimation based on fisheye cameras are studied. First, a multi-scale partition preprocessing is proposed, which can enlarge the size of small targets to improve the detection accuracy of small targets. Second, parameters learned from the public datasets without distortion is transferred to our fisheye video dataset. Then metric learning-based single shot multibox detector (MLSSD) is proposed to improve the accuracy of distorted vehicle detection. Combining metric learning and SSD network, MLSSD can significantly reduce the missing and false detection rates. Moreover, a scalable overlapping partition pooling method is proposed to explore the relations among the adjacent features in a feature map. Finally, the distance between the driving vehicle and vehicles around this vehicle is estimated based on the object detection results by the method of marker points. Experimental results show that our proposed MLSSD network significantly outperforms other networks for distorted object detection.

show abstract

Section: Network Trainingmentioning

confidence: 99%

“…Vehicle detection made great progress in the last decade. Support vector machine (SVM) [1], was used for vehicle detection. By combining the histogram of oriented gradient (HOG) and Gabor features, a composite feature was proposed to express the vehicles [2].…”

Section: Introductionmentioning

confidence: 99%

Distorted Vehicle Detection and Distance Estimation by Metric Learning-Based SSD

Zhang¹,

Jin²,

Kan³

et al. 2021

IJCIS

View full text Add to dashboard Cite

show abstract

“…Bin-Feng Lin extracted the appearance and edge features of the vehicle, while the vehicle images from different angles are trained into multiple models based on different viewpoints, and the integration of these models is used to achieve vehicle blind spot detection. 15 These approaches all require cameras to be installed on both sides of the vehicle. However, some scholars also proposed a single-camera solution.…”

Section: Introductionmentioning

confidence: 99%

A low-complexity rear vehicle detection approach based on a dual-channel millimeter-wave radar

Guo,

Yang,

Chu

et al. 2024

Fifteenth International Conference on Signal Processing Systems (ICSPS 2023)

View full text Add to dashboard Cite

A low-complexity rear vehicle detection approach based on a dual-channel millimeter-wave radar is presented in this paper. The main task is to detect whether there are vehicles approaching on both rear sides of the vehicle, and to give an early warning when the relative distance between the two vehicles is less than the early warning range. The difficulty in accurately detecting an approaching target vehicle lies in the fact that the vehicle is driving in a complex traffic scene and there are metal roadblocks in the road environments. In this paper, firstly, in order to reduce the complexity, the cascaded distance and angle of the potential target calculation is adopted to achieve the localization of the potential target. Then, rough recognition of vehicle targets and roadblocks is performed by clustering algorithm and structural features extraction. Since the features of some of the roadblocks are similar to those of the vehicle targets, secondary recognition is required to classify the vehicle targets and roadblocks by the target motion trend and trajectory length. The experimental results show that the average detection rate is 91.13% and the average false detection rate is 0.48% in different traffic scenarios.

show abstract

“…Vision systems for blind angle detection [1], lane departure warning [2], collision avoidance [3], and lidar-based systems have been widely applied in vehicle detection [4]. In spite of these advances, the latest trends have been focused on wireless communications -both vehicle-to-vehicle (V2V) [5,6] and vehicle-to-infrastructure (V2I) [7,8]-to perceive the environment as precisely as possible.…”

Section: Introductionmentioning

confidence: 99%

Cooperative controllers for highways based on human experience

Pérez

Milanés

Godoy

et al. 2013

Expert Systems with Applications

View full text Add to dashboard Cite

The AUTOPIA program has been working on the development of intelligent autonomous vehicles for the last ten years. Its latest advances have focused on the development of cooperative manoeuvres based on communications involving several vehicles. However, so far, these manoeuvres have been tested only on private tracks that emulate urban environments. The first experiments with autonomous vehicles on real highways, in the framework of the Grand Cooperative Driving Challenge (GCDC) where several vehicles had to cooperate in order to perform Cooperative Adaptive Cruise Control (CACC), are described. In this context, the main challenge was to translate, through fuzzy controllers, human driver experience to these scenarios. This communication describes the experiences deriving from this competition, specifically that concerning the controller and the system implemented in a Citröen C3.

show abstract

Incorporating appearance and edge features for vehicle detection in the blind-spot area

Cited by 10 publications

References 16 publications

Distorted Vehicle Detection and Distance Estimation by Metric Learning-Based SSD

Distorted Vehicle Detection and Distance Estimation by Metric Learning-Based SSD

A low-complexity rear vehicle detection approach based on a dual-channel millimeter-wave radar

Cooperative controllers for highways based on human experience

Contact Info

Product

Resources

About