Active learning for on-road vehicle detection: a comparative study

Sivaraman, Sayanan; Trivedi, Mohan M.

doi:10.1007/s00138-011-0388-y

Cited by 97 publications

(60 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HOG features are descriptive image features, exhibiting good detection performance in a variety of computer vision tasks, including vehicle detection, but they are generally slow to compute. HOG features have been used in a number of studies [36], [37]. In [38], the symmetry of the HOG features extracted in a given image patch, along with the HOG features themselves, was used for vehicle detection.…”

Section: A Monocular Vehicle Detectionmentioning

confidence: 99%

“…In [24], Haar features were extracted to detect the front faces of following vehicles, which were captured with a rear-facing camera. Haar-like features have been extensively used to detect the rear faces of preceding vehicles, using a forward-facing camera [37], [41]- [49]. Side profiles of vehicles have been also detected using Haar-like features [22], by detecting the front and rear wheels.…”

Section: A Monocular Vehicle Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis

Sivaraman

Trivedi

2013

IEEE Trans. Intell. Transport. Syst.

Self Cite

811

322

View full text Add to dashboard Cite

Abstract-This paper provides a review of the literature in on-road vision-based vehicle detection, tracking, and behavior understanding. Over the past decade, vision-based surround perception has progressed from its infancy into maturity. We provide a survey of recent works in the literature, placing vision-based vehicle detection in the context of sensor-based on-road surround analysis. We detail advances in vehicle detection, discussing monocular, stereo vision, and active sensor-vision fusion for on-road vehicle detection. We discuss vision-based vehicle tracking in the monocular and stereo-vision domains, analyzing filtering, estimation, and dynamical models. We discuss the nascent branch of intelligent vehicles research concerned with utilizing spatiotemporal measurements, trajectories, and various features to characterize on-road behavior. We provide a discussion on the state of the art, detail common performance metrics and benchmarks, and provide perspective on future research directions in the field.

show abstract

Section: A Monocular Vehicle Detectionmentioning

confidence: 99%

Section: A Monocular Vehicle Detectionmentioning

confidence: 99%

Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis

Sivaraman

Trivedi

2013

IEEE Trans. Intell. Transport. Syst.

Self Cite

811

322

View full text Add to dashboard Cite

show abstract

“…Seven video sequences V [1][2][3][4][5][6][7] have been used to evaluate the algorithm performances (V 1-3 are from pedestrian detection sequences in Ref. [8] and V [4][5][6][7] have been used in Refs.…”

Section: Trackers and Datasetmentioning

confidence: 99%

“…Target detection and tracking are the two import part of visual perception, recent comprehensive reviews of computer vision based vehicle and pedestrian detection can be found in Refs. [7] and [8]. However target tracking for autonomous driving has not been driven enough attention.…”

Section: Introductionmentioning

confidence: 99%

Review on Kernel based Target Tracking for Autonomous Driving

Wang

Yue

Dong

et al. 2016

Journal of Information Processing

View full text Add to dashboard Cite

Significant progress has been made in the field of autonomous driving during the past decades. However, fully autonomous driving in urban traffic is still extremely difficult in the near future. Visual tracking of vehicles or pedestrians is an essential part of autonomous driving. Among these tracking methods, kernel-based object tracking is an effective means of tracking in video sequences. This paper reviews the kernel theory adopted in target tracking of autonomous driving and makes a qualitative and quantitative comparison among several well-known kernel based methods. The theoretical and experimental analysis allow us to conclude that the kernel based online subspace learning algorithm achieves a good trade-off between the stability and real-time processing for target tracking in the practical application environments of autonomous driving. This paper reports on the result of evaluating the performances of five algorithms by using seven video sequences.

show abstract

“…Computer vision algorithms like Hough's Transform, Canny Edge detection and HAAR classifiers were applied to meet the objectives. The integrated module was analyzed and tested in different terrains and various lighting condition to produce an accurate and robust real-time assistance system (Sivaraman et al, 2014). iCar is an innovative prototype in the Information Technology with minimum hardware like low cost webcams.…”

Section: Introductionmentioning

confidence: 99%

i-Car: An Intelligent and Interactive Interface for Driver Assistance System

Kumar¹,

Ahmed²,

Shetty³

et al. 2014

Sci. Technol. Arts Res. J.

View full text Add to dashboard Cite

Article InformationThe aim of the present research was to reduce accidents by assisting the driver in various aspects of driving such as lane detection, pedestrian and car detection, driver drowsiness detection and rear view parking assistance. The methodology combines the computer vision techniques with pattern recognition, feature extraction, machine learning, object recognition, human computer interaction and parallel processing in a nutshell. The proposed system provides robust extraction of lane markings in various types and alerts the driver attempting to drift from the lane. It also detects the pedestrians and cars which are at a vulnerable distance to be hit by the vehicle and alarms the driver well ahead of time. The system uses eye closure based decision algorithm to detect driver drowsiness in all conditions and also warns by interactive voice early enough to avoid the accidents. It also assists the driver while reversing the vehicle, by providing a clear view of his blind spot areas. Computer vision algorithms like Hough's Transform, Canny Edge detection and HAAR classifiers were applied to meet the objectives. The integrated module was analyzed and tested in different terrains and various lighting condition to produce an accurate and robust real-time assistance system (Sivaraman et al., 2014). iCar is an innovative prototype in the Information Technology with minimum hardware like low cost webcams. It emerged as an Interactive Technology with an interactive audio, visual, touch and touch-less interfaces. These can assist to avoid accidents in the world by intelligently ignoring certain hardware sensors like IR, UV, Acoustic, Proximity and mechanical devices like costlier LIDAR (Light Detection and Ranging) fitted in Google Car. Present research findings outperform the state of the art research like CalTech (Aly et al., 1997). Attempts of depth sensing even using Microsoft Kinect could be ignored by the present technology, the iCar.

show abstract

Active learning for on-road vehicle detection: a comparative study

Cited by 97 publications

References 29 publications

Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis

Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis

Review on Kernel based Target Tracking for Autonomous Driving

i-Car: An Intelligent and Interactive Interface for Driver Assistance System

Contact Info

Product

Resources

About