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.
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.
“…In [9], the effect of varying the resolution of training examples for vehicle classifiers was explored, using rectangular features and Adaboost classification [7]. Rectangular features and Adaboost were also used in [21], integrated in an active learning framework for improved on-road performance.…”
Section: B Vehicle Detectionmentioning
confidence: 99%
“…While prior studies in vehicle detection explored the effect on vehicle detection performance of feature sets [10], image resolution [9], and classifiers [23], it is shown in [21], [22] the significant contribution that active learning brings to onroad vehicle detection. Active learning refers to a paradigm in which during learning process, the most informative examples are chosen for training a discriminative classifier [4].…”
Section: B Active Learning For Vehicle Detectionmentioning
confidence: 99%
“…The set of Haar-like rectangular features is well suited to detecting vehicles, as they respond strongly to vertical and horizontal edges and bars, as well as symmetric structures [27], [9]. The Adaboost classifier uses the the Haar-like feature responses as weak learners, and makes a decision based on a weighted majority of the feature responses [7].…”
Section: B Active Learning For Vehicle Detectionmentioning
Abstract-In this paper, we present improved lane tracking using vehicle localization. Lane markers are detected using a bank of steerable filters, and lanes are tracked using Kalman filtering. On-road vehicle detection has been achieved using an active learning approach, and vehicles are tracked using a Condensation particle filter. While most state-of-the art lane tracking systems are not capable of performing in high-density traffic scenes, the proposed framework exploits robust vehicle tracking to allow for improved lane tracking in high density traffic. Experimental results demonstrate that lane tracking performance, robustness, and temporal response are significantly improved in the proposed framework, while also tracking vehicles, with minimal additional hardware requirements.
“…Appearance-based template matching methods that use kernel features such as wavelet, Gabor filters, and Haarlike features have been successfully applied to vehicle detection [11,12,13]. It is expected to work well for construction equipment since it has similar appearance to vehicle in terms of rigidity and angular characteristics Recently simultaneous process of segmentation and recognition has become prevalent for object recognition [14,15].…”
Vision based tracking can provide the spatial location of project related entities such as equipment, workers, and materials in a large-scale congested construction site. It tracks entities in a video stream by inferring their motion. To initiate the process, it is required to determine the pixel areas of the entities to be tracked in the following consecutive video frames. For the purpose of fully automating the process, this paper presents an automated way of initializing trackers using Semantic Texton Forests (STFs) method. STFs method performs simultaneously the segmentation of the image and the classification of the segments based on the low-level semantic information and the context information. In this paper, STFs method is tested in the case of wheel loaders recognition. In the experiments, wheel loaders are further divided into several parts such as wheels and body parts to help learn the context information. The results show 79% accuracy of recognizing the pixel areas of the wheel loader. These results signify that STFs method has the potential to automate the initialization process of vision based tracking.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.