IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, VOL. 14, NO. 4, DECEMBER 2013 1597 Vehicle Detection by Independent Parts for Urban Driver Assistance Sayanan Sivaraman, Member, IEEE, and Mohan Manubhai Trivedi, Fellow, IEEE Abstract—In this paper, we introduce vehicle detection by in- dependent parts (VDIP) for urban driver assistance. In urban environments, vehicles appear in a variety of orientations, i.e., oncoming, preceding, and sideview. Additionally, partial vehicle occlusions are common at intersections, during entry and exit from the camera’s field of view, or due to scene clutter. VDIP provides a lightweight robust framework for detecting oncoming, preceding, sideview, and partially occluded vehicles in urban driving. In this paper, we use active learning to train independent-part detectors. A semisupervised approach is used for training part-matching classification, which forms sideview vehicles from independently detected parts. The hierarchical learning process yields VDIP, featuring efficient evaluation and robust performance. Parts and vehicles are tracked using Kalman filtering. The fully implemented system is lightweight and runs in real time. Extensive quantitative analysis on real-world on-road data sets is provided. Index Terms—Active learning, active safety, computer vision, detection by parts, machine learning, occlusions, vehicle detection. I. I NTRODUCTION I N THE United States, urban automotive collisions account for some 43% of fatal crashes. Over the past decade, while the incidence of rural and highway accidents in the United States has slowly decreased, the incidence of urban accidents has increased by 9%. Tens of thousands of drivers and pas- sengers die on the roads each year, with most fatal crashes involving more than one vehicle [1]. Research and develop- ment efforts in the areas of advanced sensing, environmental perception, and intelligent driver assistance systems present an opportunity to help save lives and reduce the number of on-road fatalities. Over the past decade, there has been significant re- search effort dedicated to the development of intelligent driver assistance systems, intended to enhance safety by monitoring the driver and the on-road environment [2]. In particular, on-road detection of vehicles has been a topic of great interest to researchers over the past decade [3]. A variety of sensing modalities has become available for on-road vehicle detection, including radar, lidar, and computer vision. As production vehicles begin to include on-board cameras for lane tracking and other purposes, it is advantageous and cost Manuscript received July 12, 2012; revised December 14, 2012 and March 18, 2013; accepted May 10, 2013. Date of publication June 14, 2013; date of current version November 26, 2013. This work was supported in part by the University of California Discovery Program, by Audi research, and by the Volkswagen Electronics Research Laboratory, Belmont, CA. The Associate Editor for this paper was Prof. L. Li. The authors are with the Laboratory for Intelligent and Safe Automo- biles, University of California, San Diego, CA 92093-0434 USA (e-mail: ssivaram@ucsd.edu; mtrivedi@ucsd.edu). Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org. Digital Object Identifier 10.1109/TITS.2013.2264314 Fig. 1. (Top) Urban driving environment features oncoming, preceding, and sideview vehicles. (Bottom) Vehicles appear partially occluded as they enter and exit the camera’s field of view. effective to pursue vision as a modality for detecting vehicles on the road. Vehicle detection using computer vision is a challenging problem [3]–[6]. Roads are dynamic environments, featuring effects of ego-motion and relative motion, and video scenes featuring high variability in background and illumi- nation conditions. Further, vehicles encountered on the road exhibit high variability in size, shape, color, make, and model. The urban driving environment introduces further challenges [13]. In urban driving, frequent occlusions and a variety of vehicle orientations make vehicle detection difficult, whereas visual clutter tends to increase the false-positive rate [14]. Fully visible vehicles are viewed in a variety of orientations, includ- ing oncoming, preceding, and sideview. Cross traffic is subject to frequent partial occlusions, particularly upon entry and exit from the camera’s field of view. Fig. 1 shows this concept. Many studies of on-road vehicle detection have detected fully visible vehicles. In this paper, we also detect and track partially occluded vehicles. In this paper, we introduce vehicle detection by indepen- dent parts (VDIP). Vehicle-part detectors are trained using 1524-9050 © 2013 IEEE