Sensor based vehicle detection and classification - a systematic review

Singhal, Nikita; Prasad, None Lalji

doi:10.1504/ijesms.2022.122731

Cited by 6 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the past decade, autonomous vehicles [1][2][3][4] have been widely studied in terms of recognizing obstacles, such as road lines, other vehicles, or pedestrians, and planning the optimal path in the road environment. Although many studies have been conducted on path planning after line detection and on vehicle recognition [5][6][7], pedestrian recognition research has scarcely been conducted except regarding pedestrian detection [8][9][10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Binary Dense SIFT Flow Based Position-Information Added Two-Stream CNN for Pedestrian Action Recognition

et al. 2022

View full text Add to dashboard Cite

Pedestrian behavior recognition in the driving environment is an important technology to prevent pedestrian accidents by predicting the next movement. It is necessary to recognize current pedestrian behavior to predict future pedestrian behavior. However, many studies have recognized human visible characteristics such as face, body parts or clothes, but few have recognized pedestrian behavior. It is challenging to recognize pedestrian behavior in the driving environment due to the changes in the camera field of view due to the illumination conditions in outdoor environments and vehicle movement. In this paper, to predict pedestrian behavior, we introduce a position-information added two-stream convolutional neural network (CNN) with multi task learning that is robust to the limited conditions of the outdoor driving environment. The conventional two-stream CNN is the most widely used model for human-action recognition. However, the conventional two-stream CNN based on optical flow has limitations regarding pedestrian behavior recognition in a moving vehicle because of the assumptions of brightness constancy and piecewise smoothness. To solve this problem for a moving vehicle, the binary descriptor dense scale-invariant feature transform (SIFT) flow, a feature-based matching algorithm, is robust in moving-pedestrian behavior recognition, such as walking and standing, in a moving vehicle. However, recognizing cross attributes, such as crossing or not crossing the street, is challenging using the binary descriptor dense SIFT flow because people who cross the road or not act the same walking action, but their location on the image is different. Therefore, pedestrian position information should be added to the conventional binary descriptor dense SIFT flow two-stream CNN. Thus, learning biased toward action attributes is evenly learned across action and cross attributes. In addition, YOLO detection and the Siamese tracker are used instead of the ground-truth boundary box to prove the robustness in the action- and cross-attribute recognition from a moving vehicle. The JAAD and PIE datasets were used for training, and only the JAAD dataset was used as a testing dataset for comparison with other state-of-the-art research on multitask and single-task learning.

show abstract

Section: Introductionmentioning

confidence: 99%

Binary Dense SIFT Flow Based Position-Information Added Two-Stream CNN for Pedestrian Action Recognition

et al. 2022

View full text Add to dashboard Cite

show abstract

A deep learning-based approach for axle counter in free-flow tolling systems

Souza,

da Costa,

Szejka

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Enhancements in the structural and operational aspects of transportation are important for achieving high-quality mobility. Toll plazas are commonly known as a potential bottleneck stretch, as they tend to interfere with the normality of the flow due to the charging points. Focusing on the automation of toll plazas, this research presents the development of an axle counter to compose a free-flow toll collection system. The axle counter is responsible for the interpretation of images through algorithms based on computer vision to determine the number of axles of vehicles crossing in front of a camera. The You Only Look Once (YOLO) model was employed in the first step to identify vehicle wheels. Considering that several versions of this model are available, to select the best model, YOLOv5, YOLOv6, YOLOv7, and YOLOv8 were compared. The YOLOv5m achieved the best result with precision and recall of 99.40% and 98.20%, respectively. A passage manager was developed thereafter to verify when a vehicle passes in front of the camera and store the corresponding frames. These frames are then used by the image reconstruction module which creates an image of the complete vehicle containing all axles. From the sequence of frames, the proposed method is able to identify when a vehicle was passing through the scene, count the number of axles, and automatically generate the appropriate charge to be applied to the vehicle.

show abstract