scholarly journals Vehicle pose estimation for vehicle detection and tracking based on road direction

2017 ◽  
Vol 3 (1) ◽  
pp. 35
Author(s):  
Adhi Prahara ◽  
Ahmad Azhari ◽  
Murinto Murinto
Keyword(s):  
Vehicle Detection ◽  
Training Data ◽  
Support Vector ◽  
Traffic Surveillance ◽  
Vehicle Performance ◽  
Surveillance Camera ◽  
Detection And Tracking ◽  
Vehicle Detection And Tracking ◽  
Different Color ◽  
Linear Svm

Vehicle has several types and each of them has different color, size, and shape. The appearance of vehicle also changes if viewed from different viewpoint of traffic surveillance camera. This situation can create many possibilities of vehicle poses. However, the one in common, vehicle pose usually follows road direction. Therefore, this research proposes a method to estimate the pose of vehicle for vehicle detection and tracking based on road direction. Vehicle training data are generated from 3D vehicle models in four-pair orientation categories. Histogram of Oriented Gradients (HOG) and Linear-Support Vector Machine (Linear-SVM) are used to build vehicle detectors from the data. Road area is extracted from traffic surveillance image to localize the detection area. The pose of vehicle which estimated based on road direction will be used to select a suitable vehicle detector for vehicle detection process. To obtain the final vehicle object, vehicle line checking method is applied to the vehicle detection result. Finally, vehicle tracking is performed to give label on each vehicle. The test conducted on various viewpoints of traffic surveillance camera shows that the method effectively detects and tracks vehicle by estimating the pose of vehicle. Performance evaluation of the proposed method shows 0.9170 of accuracy and 0.9161 of balance accuracy (BAC).

scholarly journals V-DaT: A Robust method for Vehicle Detection and Tracking

2021 ◽  
Vol 12 (2) ◽  
pp. 2492-2505
Author(s):  
Latha Anuj , Et. al.
Keyword(s):  
Background Subtraction ◽  
Vehicle Detection ◽  
Morphological Operations ◽  
Traffic Surveillance ◽  
Moving Vehicle ◽  
Directional Filtering ◽  
Detection And Tracking ◽  
Algorithmic Optimization ◽  
Vehicle Detection And Tracking ◽  
Moving Vehicle Detection

Vision-based traffic surveillance has been one of the most promising fields for improvement and research. Still, many challenging problems remain unsolved, such as addressing vehicle occlusions and reducing false detection. In this work, a method for vehicle detection and tracking is proposed. The proposed model considers background subtraction concept for moving vehicle detection but unlike conventional approaches, here numerous algorithmic optimization approaches have been applied such as multi-directional filtering and fusion based background subtraction, thresholding, directional filtering and morphological operations for moving vehicle detection. In addition, blob analysis and adaptive bounding box is used for Detection and Tracking. The Performance of Proposed work is measured on Standard Dataset and results are encouraging.

scholarly journals Boosting Multi-Vehicle Tracking with a Joint Object Detection and Viewpoint Estimation Sensor

Sensors ◽  
2019 ◽  
Vol 19 (19) ◽  
pp. 4062 ◽  
Author(s):  
Roberto López-Sastre ◽  
Carlos Herranz-Perdiguero ◽  
Ricardo Guerrero-Gómez-Olmedo ◽  
Daniel Oñoro-Rubio ◽  
Saturnino Maldonado-Bascón
Keyword(s):  
Object Detection ◽  
Vehicle Detection ◽  
Traffic Monitoring ◽  
Vehicle Tracking ◽  
Object Localization ◽  
Support Vector ◽  
Detection And Tracking ◽  
Vehicle Detection And Tracking ◽  
Monitoring Applications ◽  
Viewpoint Estimation

In this work, we address the problem of multi-vehicle detection and tracking for traffic monitoring applications. We preset a novel intelligent visual sensor for tracking-by-detection with simultaneous pose estimation. Essentially, we adapt an Extended Kalman Filter (EKF) to work not only with the detections of the vehicles but also with their estimated coarse viewpoints, directly obtained with the vision sensor. We show that enhancing the tracking with observations of the vehicle pose, results in a better estimation of the vehicles trajectories. For the simultaneous object detection and viewpoint estimation task, we present and evaluate two independent solutions. One is based on a fast GPU implementation of a Histogram of Oriented Gradients (HOG) detector with Support Vector Machines (SVMs). For the second, we adequately modify and train the Faster R-CNN deep learning model, in order to recover from it not only the object localization but also an estimation of its pose. Finally, we publicly release a challenging dataset, the GRAM Road Traffic Monitoring (GRAM-RTM), which has been especially designed for evaluating multi-vehicle tracking approaches within the context of traffic monitoring applications. It comprises more than 700 unique vehicles annotated across more than 40.300 frames of three videos. We expect the GRAM-RTM becomes a benchmark in vehicle detection and tracking, providing the computer vision and intelligent transportation systems communities with a standard set of images, annotations and evaluation procedures for multi-vehicle tracking. We present a thorough experimental evaluation of our approaches with the GRAM-RTM, which will be useful for establishing further comparisons. The results obtained confirm that the simultaneous integration of vehicle localizations and pose estimations as observations in an EKF, improves the tracking results.

Sign in / Sign up

Export Citation Format

Share Document