Vision-based Lane-Vehicle Detection and Tracking

Lim, King Hann; Seng, Kah Phooi; Ang, Li-Minn; Chin, Siew Wen

doi:10.1063/1.3256243

Cited by 18 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, the grey level threshold separating road and the shadow under a vehicle is not provided in [20]. An alternative solution is proposed in [21] and later used in [22,23,24,25,26,27,28,29], where a coarse approximation of the free driving space is obtained by defining the lowest central region in the image delimited by edges. A normal distribution is assumed for the grey levels of the free driving space, and the shadow under a vehicle is defined as a region with intensity smaller than a threshold m − 3 σ , where m and σ are respectively the mean and standard deviation of the grey levels of road pixels.…”

Section: Related Workmentioning

confidence: 99%

Shadow-Based Vehicle Detection in Urban Traffic

Ibarra-Arenado

Tjahjadi

Pérez-Oria

et al. 2017

Sensors

View full text Add to dashboard Cite

Vehicle detection is a fundamental task in Forward Collision Avoiding Systems (FACS). Generally, vision-based vehicle detection methods consist of two stages: hypotheses generation and hypotheses verification. In this paper, we focus on the former, presenting a feature-based method for on-road vehicle detection in urban traffic. Hypotheses for vehicle candidates are generated according to the shadow under the vehicles by comparing pixel properties across the vertical intensity gradients caused by shadows on the road, and followed by intensity thresholding and morphological discrimination. Unlike methods that identify the shadow under a vehicle as a road region with intensity smaller than a coarse lower bound of the intensity for road, the thresholding strategy we propose determines a coarse upper bound of the intensity for shadow which reduces false positives rates. The experimental results are promising in terms of detection performance and robustness in day time under different weather conditions and cluttered scenarios to enable validation for the first stage of a complete FACS.

show abstract

Section: Related Workmentioning

confidence: 99%

Shadow-Based Vehicle Detection in Urban Traffic

Ibarra-Arenado

Tjahjadi

Pérez-Oria

et al. 2017

Sensors

View full text Add to dashboard Cite

show abstract

“…For the identification of the obstacle regions in the image, solutions include region segmentation [6,7], motion based analysis [8,9], or appearance analysis, either through heuristics such as symmetry [10,11], or through the use of machine learning [12,13]. For extracting the 3D position of the obstacle, monocular vision uses constraints imposed on the structure of the environment, such as the condition that the road is flat, which leads to the measurement of the points on the road by Inverse Perspective Mapping (IPM) [14,15].…”

Section: Related Workmentioning

confidence: 99%

Generic Dynamic Environment Perception Using Smart Mobile Devices

Danescu

Itu

Petrovai

2016

Sensors

View full text Add to dashboard Cite

The driving environment is complex and dynamic, and the attention of the driver is continuously challenged, therefore computer based assistance achieved by processing image and sensor data may increase traffic safety. While active sensors and stereovision have the advantage of obtaining 3D data directly, monocular vision is easy to set up, and can benefit from the increasing computational power of smart mobile devices, and from the fact that almost all of them come with an embedded camera. Several driving assistance application are available for mobile devices, but they are mostly targeted for simple scenarios and a limited range of obstacle shapes and poses. This paper presents a technique for generic, shape independent real-time obstacle detection for mobile devices, based on a dynamic, free form 3D representation of the environment: the particle based occupancy grid. Images acquired in real time from the smart mobile device’s camera are processed by removing the perspective effect and segmenting the resulted bird-eye view image to identify candidate obstacle areas, which are then used to update the occupancy grid. The occupancy grid tracked cells are grouped into obstacles depicted as cuboids having position, size, orientation and speed. The easy to set up system is able to reliably detect most obstacles in urban traffic, and its measurement accuracy is comparable to a stereovision system.

show abstract

“…These methods depend on contours (the boundaries of vehicle) which are updated dynamically in successive images of vehicle in Tracking Vehicle Process [36]. These methods provide more efficient descriptions of objects than Region-Based Methods and have been successfully applied to practice.…”

Section: Contour Tracking Methodsmentioning

confidence: 99%