Robust Obstacle Detection Based on Dense Disparity Maps

Miled, Wided; Pesquet, J.-C.; Parent, Michel

doi:10.1007/978-3-540-75867-9_143

Cited by 9 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Triclops automatically performs image rectification and stereo processing in real time. The Bumblebee® system provides 3D range data through a fully automated pre-calibration process based on the acquired images [18]. The range data have a maximum resolution of 1280 × 960 pixels at 15 frames per second (FPS); the frame rate can be increased to 30 FPS at resolutions of up to 1024 × 768.…”

Section: Data Acquisitionmentioning

confidence: 99%

3D structural component recognition and modeling method using color and 3D data for construction progress monitoring

Son¹,

Kim²

2010

Automation in Construction

122

View full text Add to dashboard Cite

Section: Data Acquisitionmentioning

confidence: 99%

3D structural component recognition and modeling method using color and 3D data for construction progress monitoring

Son¹,

Kim²

2010

Automation in Construction

122

View full text Add to dashboard Cite

“…Vision based obstacle detection systems are further classified as range-based systems and appearance-based systems. Range-based systems detect obstacles on the basis of disparity calculations [5] - [7], range data [8] and ground plane estimation [9]. All range-based systems make use of computationally expensive complex algorithms and have difficulty detecting small or flat objects on the ground.…”

Section: Related Workmentioning

confidence: 99%

A Novel Color Coherence Vector Based Obstacle Detection Algorithm for Textured Environments

Mittal¹,

Sofat²

2013

IJCTE

View full text Add to dashboard Cite

This paper presents a novel obstacle detection algorithm that makes use of color information and color coherence vectors for robust obstacle detection. The algorithm makes use of color cue to classify a pixel in an image as an obstacle or a path. Color is one of the prominent image features. Color information is readily available as input from a color camera. Our algorithm makes use of coherence vectors for representation and matching instead of histograms. A color histogram provides no spatial information. It merely describes the color information present in an image. Color coherence vectors represent pixels as either coherent or incoherent. Color coherence vectors prevent coherent pixels from getting matched with incoherent pixels. The color histogram cannot make such fine distinction. The algorithm is tested with a challenging indoor and outdoor image set. Test results show that our algorithm performs better than available color based obstacle detection approaches.

show abstract

“…But it is the system work only for the robot moving on the ground. [3] compute a surface norm vector for each stereo point from disparity image in camera coordinate. Then they make a decision whether there is a obstacle in front of the robot depend on the surface norm vector.…”

Section: Related Workmentioning

confidence: 99%

The development of stereo vision system for UAVs

Chen¹

View full text Add to dashboard Cite

Quadcopter research and application have drawn great attention in the past years. Recent successful commercialization of quadcopter make it become a popular tool applied in aerial photography, surveillance, Precision Farming. There is no doubt that in these applications, environment perception is a core capability for safe flight, in the meantime, it is a challenging problem in the real flight environment. This thesis presents the stereo vision system for the safe flight of a quadcopter. Firstly, we develop a traditional parallel pinhole stereo vision for depth capture after an accurate calibration procedure. A long baseline and rigid mount of the stereo camera enable the quadcopter to measure a long range distance from 0.5m to 15m. The Field of View of the pinhole stereo vision system is 70 •. Secondly, we explore a novel Up & Down Configuration fisheye stereo vision system which enable the quadcopter to perceive the environment with 360 • Field of View just in a single frame. x

show abstract

Robust Obstacle Detection Based on Dense Disparity Maps

Cited by 9 publications

References 9 publications

3D structural component recognition and modeling method using color and 3D data for construction progress monitoring

3D structural component recognition and modeling method using color and 3D data for construction progress monitoring

A Novel Color Coherence Vector Based Obstacle Detection Algorithm for Textured Environments

The development of stereo vision system for UAVs

Contact Info

Product

Resources

About