Deep Convolutional Neural Network (DCNN) is a class of machine learning algorithms that has wide application in pattern recognition, image recognition and video analysis. Convolutional layers in the network extract va...
详细信息
ISBN:
(纸本)9781538673782
Deep Convolutional Neural Network (DCNN) is a class of machine learning algorithms that has wide application in pattern recognition, image recognition and video analysis. Convolutional layers in the network extract various features from a set of inputs and adapt parameters, before they do the classification. Training of DCNN is computationally intensive and has large memory requirement, but offers multiple degrees of parallelism, as similar structures are needed for computation at various intermediate stages. Training using a general purpose processing unit does not utilize parallelism of the network, and hence, is very time and energy inefficient. In this paper, we propose a coprocessor for accelerating the training of Convolutional Neural Network using a Xilinx Kintex Ultrascale XCKU085 based HTG-K800 FPGA board. DCNN is trained using back propagation algorithm. The coprocessor can be configured for a new network structure by changing the contents of Block Memory in the FPGA, without re-synthesizing and implementing using the design software. The reconfigurability through DDR can be supported with the architecture but is not implemented. The implementation achieves a maximum throughput of 280GOp/s.
Video sensor capabilities and sophistication has improved to the point that they are being utilized in vast and diverse applications. Many such applications are now on the verge of providing too much video information...
详细信息
Video sensor capabilities and sophistication has improved to the point that they are being utilized in vast and diverse applications. Many such applications are now on the verge of providing too much video information reducing the ability to review, categorize, and process the immense amounts of video. Advancement in other technology areas such as Global Positioning System (GPS) processors and single board computers have paved the way for a new development of smart video sensors. A need exists to be able to identify stationary objects, such as buildings, and register their location back to the GIS database. Furthermore, transmitting large imagestreams from remote locations would quickly use available band width (BW) precipitating the need for processing to occur at the sensor location. This paper addresses the problem of automatic target recognition. Utilizing an Adaptive Resonance Theory approach to cluster templates of target buildings processing and memory requirements can be significantly reduced allowing for processing at the sensor. The results show that the network successfully classifies targets and their location in a virtual test bed environment eventually leading to autonomous and passive information processing.
There is an exponential volume of captured images, millions of captures taken every night being processed and scrutinized. Big Data analysis has become essential for the study of the solar system, discovery and orbita...
ISBN:
(数字)9781728157245
ISBN:
(纸本)9781728157252
There is an exponential volume of captured images, millions of captures taken every night being processed and scrutinized. Big Data analysis has become essential for the study of the solar system, discovery and orbital knowledge of the asteroids. This analysis often requires more advanced algorithms capable of processing the available data and solve the essential problems in almost real time. One such problem that needs very rapid investigation involves the detection of Near Earth Asteroids(NEAs) and their orbit refinement which should answer the question "will the Earth collide in the future with any hazardous asteroid?". This paper proposes a cloud distributed architecture meant to render near real-time results, focusing on the imagestacking techniques aimed to detect very faint moving objects, and pairing of unknown objects with known orbits for asteroid discovery and identification.
This study presents an innovative approach to animal classification and recognition utilizing machine learning and deep learning methodologies. Leveraging advanced algorithms, the proposed system achieves remarkable a...
详细信息
ISBN:
(数字)9798350378078
ISBN:
(纸本)9798350378085
This study presents an innovative approach to animal classification and recognition utilizing machine learning and deep learning methodologies. Leveraging advanced algorithms, the proposed system achieves remarkable accuracy in identifying diverse animal species. By integrating sophisticated imageprocessing techniques, the system enhances image quality, improving overall performance. The research demonstrated that the SVM model combined with deep neural network-based feature extraction achieved the highest accuracy of 95.65%. This paper represents a significant stride toward improving the precision and efficiency of animal classification, offering promising applications in biodiversity conservation and ecological monitoring by using advanced feature extraction approach with deep learning.
暂无评论