Parallel Processing Technique for High Speed Object Recognition
Rasiq S. M,S. Krishnakumar +1 more
TL;DR: This work introduces a novel method for recognizing a discriminative object at a very high speed based on self learning high speed parallel processing devices which is made for doing some kinds of particular jobs.
read more
Abstract: this work, we introduce a novel method for recognizing a discriminative object at a very high speed. The system is based on self learning high speed parallel processing devices. The system processes video streams at speed of 1000 frames per second or more. For high speed object recognition using sequential computing from an image of a video having thousands of frames per second and each image frame consists of thousands of pixels, we need very much time for executing complicated algorithms. In the traditional way of computing and recognizing systems are very time consuming compared to our system because the traditional systems use sequential computation for recognizing, with some complicated functions. If we use other types of parallel processors like ANN for processing each pixel or group of pixels, those systems need programming and giving data to such large number of processors are practically difficult. Here we have used a self learning parallel processor device which is made for doing some kinds of particular jobs. This parallel processing devices are easy to manipulate and can be trained simultaneously. It contains memory for storing data comparators for comparing with previously stored memory etc. Training as well as functioning are in real time even if the system process thousands of image frames per second.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Fast-Efficient parallel processing algorithm for straight line detection
TL;DR: This work presents a novel method for detecting straight lines in an image at a very high speed with optimum number of processors and their functionalities that can be used to extract straight lines directly from an image without noise removal and pre-processing.
A review of the Multiple Object Detection, Tracking and Recognition in Video Surveillance Systems using different approaches
C.M. Patil,Sunitha Y. N +1 more
- 28 Jul 2019
TL;DR: Different methodologies towards such different types of moving object detection, its segmentation, histogram equalization, filtering, classification etc… are examined to examine and audit.
2
Fast Color Straight Line Pattern Recognition in an Object Using High Speed Self Learning Devices
S. M. Rasiq,S. Krishnakumar +1 more
TL;DR: A very high-speed object recognition method using color straight line patterns is carried out using a novel self-learning device (RKD) using RKD based networks for different steps in this pattern classification.
References
Use of the Hough transformation to detect lines and curves in pictures
Richard O. Duda,Peter E. Hart +1 more
TL;DR: It is pointed out that the use of angle-radius rather than slope-intercept parameters simplifies the computation further, and how the method can be used for more general curve fitting.
•Book
Bayesian learning for neural networks
Geoffrey E. Hinton,Radford M. Neal +1 more
- 01 Jan 1995
TL;DR: Bayesian Learning for Neural Networks shows that Bayesian methods allow complex neural network models to be used without fear of the "overfitting" that can occur with traditional neural network learning methods.
4.8K
Active Structured Learning for High-Speed Object Detection
Christoph H. Lampert,Jan Peters +1 more
- 03 Sep 2009
TL;DR: This work introduces a method for learning a discriminative object tracking system based on the recent structured regression framework for object localization using a kernel function that allows fast evaluation on the GPU, and proposes an active learning method that select training examples in a data-driven way, thereby minimizing the required number of training labeling.
A High-Resolution Nonvolatile Analog Memory Cell
Christopher J. Diorio,Sunit Mahajan,Paul Hasler,Bradley A. Minch,Carver A. Mead +4 more
- 01 Jan 1995
TL;DR: A 3-transistor non-volatile analog storage cell with 14 bits effective resolution and rail-to-rail buffered voltage output is presented, which makes the cell especially attractive for use in analog neural networks.
Efficient, high-quality image contour detection
Bryan Catanzaro,Bor-Yiing Su,Narayanan Sundaram,Yunsup Lee,Mark Murphy,Kurt Keutzer +5 more
- 01 Sep 2009
TL;DR: This work examines efficient parallel algorithms for performing image contour detection, with particular attention paid to local image analysis as well as the generalized eigensolver used in Normalized Cuts, and proposes a contour detector that provides uncompromised contour accuracy.