A General Active-Learning Framework for On-Road Vehicle Recognition and Tracking

Abstract

Abstract-This paper introduces a general active-learning framework for robust on-road vehicle recognition and tracking. This framework takes a novel active-learning approach to building vehicle-recognition and tracking systems. A passively trained recognition system is built using conventional supervised learning. Using the query and archiving interface for active learning (QUAIL), the passively trained vehicle-recognition system is evaluated on an independent real-world data set, and informative samples are queried and archived to perform selective sampling. A second round of learning is then performed to build an active-learning-based vehicle recognizer. Particle filter tracking is integrated to build a complete multiple-vehicle tracking system. The active-learning-based vehicle-recognition and tracking (ALVeRT) system has been thoroughly evaluated on static images and roadway video data captured in a variety of traffic, illumination, and weather conditions. Experimental results show that this framework yields a robust efficient on-board vehicle recognition and tracking system with high precision, high recall, and good localization.Index Terms-Active safety, computer vision, intelligent driverassistance systems, machine learning.

On-board Robust Vehicle Detection Using Knowledge-based Features and Motion Trajectory

“…As Ref. [10,11], we use the following indicators to measure the algorithm performance: detection rate (DR), false alarm rate (FAR), localization, robustness, efficiency. In this paper, the performance of a detection module is quantified by the metrics which are widely used [9][10][11]: detection rate, false alarm rate and average processing time per frame.…”

“…Appearance-based approaches are more widely used in HV phase, the brief steps of these methods are: first capture the variability of vehicle appearance and then learn the characteristics of the vehicle class from a set of training images. Learning-based methods yield a decent performance in the recent literatures, such as Haar+Adaboost [7], HoG+SVM [8], PCA-ICA+GMM [9], minimum Mahalanobis distance classifier [2,10], HOG+Adaboost [5] and Active-learning framework [11]. VT is processed to make sure the vehicles in video sequences are continuously detected.…”

Overtaking & receding vehicle detection for driver assistance and naturalistic driving studies

“…Vehicle detection [2], [3], [4], [5], lane detection [6], [7], [8], pedestrian detection [9] and higher order tasks involving lanes and vehicles such as trajectory analysis [10], [11], [12] using different sensing modalities, is therefore an active area of research for automotive active safety systems, and in offline data analysis for naturalistic driving studies (NDS) also [13], [14], [15].…”

“…While on-road vehicle detection techniques such as [2], [3], [4] detect vehicles that are visible partially or fully with varying levels of accuracy and efficiency, techniques such as [17], [18], [19] are particularly dealing with overtaking vehicles, which is relatively less explored [17]. Fig.…”

Vehicle Iconic Surround Observer: Visualization platform for intelligent driver support applications

“…4 shows 4 surround videos on the left hand side and 3 driver video streams on the right. Rectilinear cameras view through the front windshield (for lane [11] and vehicle [12] detection) and two out of the rear window while an omni-directional camera provides a full 360…”