A Novel Distance Estimation Method Leading a Forward Collision Avoidance Assist System for Vehicles on Highways

Liu, Liang-Chien; Fang, Chiung‐Yao; Chen, Sei-Wang

doi:10.1109/tits.2016.2597299

Cited by 40 publications

(28 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, some methods introduce machine learning classifiers to train appearance features. Liu et al used an AdaBoost classifier trained with the Haar-like features to detect vehicles [16]. Wei et al proposed to train a support vector machine (SVM) by combining the features of Haar and histogram of oriented gradients (HOG) to extract vehicle positions [17].…”

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

“…The distance estimation accuracy depends on the accuracy of the parameters in formulae Equations (4) and (A3) and the approximations used to obtain Equation (6). We modeled the distributions of these parameter measurements as normal distributions, for set-ups similar to the one used in our dynamic test.…”

Section: Estimation Of Measurement Noise Levelmentioning

confidence: 99%

“…These techniques typically combine object detection networks with geometric techniques but also employ extra information to accurately estimate the distances. These features include the presence of lane markings [4], or the specific geometry of cars [5]. However, in the application of detecting bicycles in triathlon races, neither of these additional features can be used.…”

Section: Introductionmentioning

confidence: 99%

Camera-Based System for Drafting Detection While Cycling

Allebosch

Bossche

Veelaert

et al. 2020

Sensors

View full text Add to dashboard Cite

Drafting involves cycling so close behind another person that wind resistance is significantly reduced, which is illegal during most long distance and several short distance triathlon and duathlon events. In this paper, a proof of concept for a drafting detection system based on computer vision is proposed. After detecting and tracking a bicycle through the various scenes, the distance to this object is estimated through computational geometry. The probability of drafting is then determined through statistical analysis of subsequent measurements over an extended period of time. These algorithms are tested using a static recording and a recording that simulates a race situation with ground truth distances obtained from a Light Detection And Ranging (LiDAR) system. The most accurate developed distance estimation method yields an average error of 0.46 m in our test scenario. When sampling the distances at periods of 1 or 2 s, simulations demonstrate that a drafting violation is detected quickly for cyclists riding at 2 m or more below the limit, while generally avoiding false positives during the race-like test set-up and five hour race simulations.

show abstract

“…Many studies based on vision sensors have been carried out for vehicle detection and symmetrical distance estimation [14][15][16][17]. Image processing can be applied in different ways based on the features of the vision sensor.…”

Section: Introductionmentioning

confidence: 99%

“…Vehicle detection methods are mostly based on features that assume an invariable and formal shape of the vehicle. Vehicle-to-vehicle distance estimation research includes a distance estimation method based on the size of the detected vehicle [15,17,28], stereo camera-based method [16,29], and a method that compares the size of road infrastructure (lane, guide rail, etc.). Vehicle distance estimation methods are mostly based on the detected vehicle shape information [12].…”

Section: Introductionmentioning

confidence: 99%

Efficient Vehicle Detection and Distance Estimation Based on Aggregated Channel Features and Inverse Perspective Mapping from a Single Camera

Kim

2019

Symmetry

View full text Add to dashboard Cite

In this paper a method for detecting and estimating the distance of a vehicle driving in front using a single black-box camera installed in a vehicle was proposed. In order to apply the proposed method to autonomous vehicles, it was required to reduce the throughput and speed-up the processing. To do this, the proposed method decomposed the input image into multiple-resolution images for real-time processing and then extracted the aggregated channel features (ACFs). The idea was to extract only the most important features from images at different resolutions symmetrically. A method of detecting an object and a method of estimating a vehicle’s distance from a bird’s eye view through inverse perspective mapping (IPM) were applied. In the proposed method, ACFs were used to generate the AdaBoost-based vehicle detector. The ACFs were extracted from the LUV color, edge gradient, and orientation (histograms of oriented gradients) of the input image. Subsequently, by applying IPM and transforming a 2D input image into 3D by generating an image projected in three dimensions, the distance between the detected vehicle and the autonomous vehicle was detected. The proposed method was applied in a real-world road environment and showed accurate results for vehicle detection and distance estimation in real-time processing. Thus, it was showed that our method is applicable to autonomous vehicles.

show abstract

A Novel Distance Estimation Method Leading a Forward Collision Avoidance Assist System for Vehicles on Highways

Cited by 40 publications

References 29 publications

Vehicle Detection and Ranging Using Two Different Focal Length Cameras

Vehicle Detection and Ranging Using Two Different Focal Length Cameras

Camera-Based System for Drafting Detection While Cycling

Efficient Vehicle Detection and Distance Estimation Based on Aggregated Channel Features and Inverse Perspective Mapping from a Single Camera

Contact Info

Product

Resources

About