TY - CONF T1 - Canny edge detection on NVIDIA CUDA T2 - Computer Vision and Pattern Recognition Workshops, 2008. CVPRW '08. IEEE Computer Society Conference on Y1 - 2008 A1 - Luo,Yuancheng A1 - Duraiswami, Ramani KW - algorithms;connected-component KW - analysis KW - application KW - Canny KW - CUDA;computer KW - detection;feature KW - detection;NVIDIA KW - detector;filtering;graphical KW - detector;non KW - edge KW - extraction;smoothing KW - feature KW - filter KW - layers;multistep KW - methods; KW - responses;nonmaxima KW - stage;edge KW - suppression;smoothing;computer KW - VISION KW - vision;edge AB - The Canny edge detector is a very popular and effective edge feature detector that is used as a pre-processing step in many computer vision algorithms. It is a multi-step detector which performs smoothing and filtering, non-maxima suppression, followed by a connected-component analysis stage to detect ldquotruerdquo edges, while suppressing ldquofalserdquo non edge filter responses. While there have been previous (partial) implementations of the Canny and other edge detectors on GPUs, they have been focussed on the old style GPGPU computing with programming using graphical application layers. Using the more programmer friendly CUDA framework, we are able to implement the entire Canny algorithm. Details are presented along with a comparison with CPU implementations. We also integrate our detector in to MATLAB, a popular interactive simulation package often used by researchers. The source code will be made available as open source. JA - Computer Vision and Pattern Recognition Workshops, 2008. CVPRW '08. IEEE Computer Society Conference on M3 - 10.1109/CVPRW.2008.4563088 ER - TY - CONF T1 - Human detection using iterative feature selection and logistic principal component analysis T2 - Robotics and Automation, 2008. ICRA 2008. IEEE International Conference on Y1 - 2008 A1 - Abd-Almageed, Wael A1 - Davis, Larry S. KW - algorithm;logistic KW - analysis;edge KW - analysis;probability; KW - applications;principal KW - belongness KW - component KW - DETECTION KW - detection;feature KW - detection;iterative KW - detection;principal KW - extraction;filtering KW - feature KW - filtering;human KW - MAP KW - methods;object KW - PCA;object KW - probability;edge KW - selection KW - theory;iterative AB - We present a fast feature selection algorithm suitable for object detection applications where the image being tested must be scanned repeatedly to detected the object of interest at different locations and scales. The algorithm iteratively estimates the belongness probability of image pixels to foreground of the image. To prove the validity of the algorithm, we apply it to a human detection problem. The edge map is filtered using a feature selection algorithm. The filtered edge map is then projected onto an eigen space of human shapes to determine if the image contains a human. Since the edge maps are binary in nature, Logistic Principal Component Analysis is used to obtain the eigen human shape space. Experimental results illustrate the accuracy of the human detector. JA - Robotics and Automation, 2008. ICRA 2008. IEEE International Conference on M3 - 10.1109/ROBOT.2008.4543444 ER - TY - JOUR T1 - Robust and efficient detection of salient convex groups JF - Pattern Analysis and Machine Intelligence, IEEE Transactions on Y1 - 1996 A1 - Jacobs, David W. KW - complexity;computer KW - complexity;contours;image KW - computational KW - convex KW - detection;feature KW - detection;object KW - extraction;object KW - groups;computational KW - organisation;proximity;salient KW - recognition; KW - recognition;line KW - recognition;perceptual KW - segment KW - vision;edge AB - This paper describes an algorithm that robustly locates salient convex collections of line segments in an image. The algorithm is guaranteed to find all convex sets of line segments in which the length of the gaps between segments is smaller than some fixed proportion of the total length of the lines. This enables the algorithm to find convex groups whose contours are partially occluded or missing due to noise. We give an expected case analysis of the algorithm performance. This demonstrates that salient convexity is unlikely to occur at random, and hence is a strong clue that grouped line segments reflect underlying structure in the scene. We also show that our algorithm run time is O(n 2log(n)+nm), when we wish to find the m most salient groups in an image with n line segments. We support this analysis with experiments on real data, and demonstrate the grouping system as part of a complete recognition system VL - 18 SN - 0162-8828 CP - 1 M3 - 10.1109/34.476008 ER -