Detection and Classification of Moving Objects-Stereo or Time-of-Flight Images

Ghobadi, Seyed Eghbal; Hartmann, Klaus; Weihs, W.; Netramai, Chayakorn; Loffeld, Otmar; Roth, Hubert

doi:10.1109/iccias.2006.294082

Cited by 13 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For planar and untextured object surfaces, where stereo techniques clearly fail, Ghobadi et al [37] compared the results of a dynamic object detection algorithm based on SVM using stereo and ToF depth images. In the same manner, Hussmann and Liepert [38] also compared ToF and stereo vision for object pose computation.…”

Section: Object-related Tasksmentioning

confidence: 99%

“…A classical solution in the area of object modeling is the use of calibrated stereo rigs. Therefore, initial works were devoted to their comparison with [37] Dynamic object detection and classification Color and light independence PMD Hussmann and Liepert [38] Object pose Easy object/background segmentation PMD Guomundsson et al [39] Known object pose estimation Light independent / Absolute scale SR3 Beder et al [40] Surface reconstruction using patchlets ToF easily combines with stereo PMD Fuchs and May [7] Precise surface reconstruction 3D at high rate SR3/O3D100 (Depth) Dellen et al [5] 3D object reconstruction 3D at high rate SR3 (Depth) Foix et al [6] Kuehnle et al [8] Object recognition for grasping 3D allow geometric primitives search SR3 Grundmann et al [41] Collision free object manipulation 3D at high rate SR3 + stereo Reiser and Kubacki [42] Position based visual servoing 3D is simply obtained / No model needed SR3 (Depth) Gachter et al [43] Object part detection for classification 3D at high rate SR3 Shin et al [44] SR2 Klank et al [45] Mobile manipulation Easy table/object segmentation SR4 Marton et al [46] Object categorization ToF easily combines with stereo SR4 + color Nakamura et al [47] Mobile manipulation Easy table segmentation SR4 + color Saxena et al [9] Grasping unknown objects 3D at high rate SR3 + stereo Zhu et al [48] Short range depth maps ToF easily combines with stereo SR3 + stereo Lindner et al [49] Object segmentation for recognition Easy color registration PMD + color camera Fischer et al [50] Occlusion handling in virtual objects 3D at high rate PMD + color camera…”

Section: Object-related Tasksmentioning

confidence: 99%

See 1 more Smart Citation

ToF cameras for active vision in robotics

Alenyà

Foix

Torras

2014

Sensors and Actuators A: Physical

View full text Add to dashboard Cite

ToF cameras are now a mature technology that is widely being adopted to provide sensory input to robotic applications. Depending on the nature of the objects to be perceived and the viewing distance, we distinguish two groups of applications: those requiring to capture the whole scene and those centered on an object. It will be demonstrated that it is in this last group of applications, in which the robot has to locate and possibly manipulate an object, where the distinctive characteristics of ToF cameras can be better exploited.After presenting the physical sensor features and the calibration requirements of such cameras, we review some representative works highlighting for each one which of the distinctive ToF characteristics have been more essential. Even if at low resolution, the acquisition of 3D images at frame-rate is one of the most important features, as it enables quick background/foreground segmentation. A common use is in combination with classical color cameras. We present three developed applications, using a mobile robot and a robotic arm, to exemplify with real images some of the stated advantages.

show abstract

Section: Object-related Tasksmentioning

confidence: 99%

Section: Object-related Tasksmentioning

confidence: 99%

ToF cameras for active vision in robotics

Alenyà

Foix

Torras

2014

Sensors and Actuators A: Physical

View full text Add to dashboard Cite

show abstract

“…The PMD (Photonic Mixer Device) camera is a true 3D camera that directly measures the depth of scene using time of flight principle. Although PMD camera is still under intensive development but recently the tests have shown its performance outperforming stereo cameras [1]. With the proposed multiple stereo cameras hardware the PMD camera can be used instead of the stereo camera in order to open a completely new way of building photorealistic 3D map in the near future.…”

Section: Future Developmentmentioning

confidence: 99%

Real-Time Photorealistic 3D Map Building using Mobile Multiple Stereo Cameras Setup

Netramai

Roth

2007

2007 3DTV Conference

View full text Add to dashboard Cite

This work proposes a multiple stereo cameras setup as sensing device for real time photorealistic 3D map building task. Applications include 3D photorealistic capturing of historic sites, remote exploration and navigation for autonomous robots, 3DTV, entertainment industry and much more. Particular emphasis is placed on the novel multiple cameras arrangement that minimizes the weak points found on single stereo camera system and gives advantages toward the applications that require high accuracy 3D spatial and 3D geometry information, e.g. 3D mapping, 3D positioning and trajectory estimation. A hardware prototype was constructed and it shows promising performance toward real time photorealistic 3D map building task.

show abstract

“…However, they are attractive due to their cost, speed, and simplicity. They are being used in many applications in pattern recognition, computer vision and multimedia [2][3][4].…”

Section: Introductionmentioning

confidence: 99%

Super-Resolution Reconstruction Algorithm for PMD Range Image Based on Regularization

Zhang

Shen

2011

2011 Third International Conference on Intelligent Human-Machine Systems and Cybernetics

View full text Add to dashboard Cite

PMD camera is a three-dimensional imaging system based on TOF principle. In the basis on obtaining the two-dimensional gray image, this camera can capture range image and amplitude image at the same time. Their main drawbacks are low-resolution and random noise. According to this problem, this paper proposed an improved regularization method which uses adaptive weighting on the regular terms, and uses confidence as the weighted value of each pixel variance of range image to smooth each pixel in neighborhood. The experimental results demonstrate that this algorithm not only can effectively enhance the edge of range image, but also can reduce the noise and the performance of reconstruction is better improved.

show abstract

Detection and Classification of Moving Objects-Stereo or Time-of-Flight Images

Cited by 13 publications

References 8 publications

ToF cameras for active vision in robotics

ToF cameras for active vision in robotics

Real-Time Photorealistic 3D Map Building using Mobile Multiple Stereo Cameras Setup

Super-Resolution Reconstruction Algorithm for PMD Range Image Based on Regularization

Contact Info

Product

Resources

About