Persons

• Counter: 301 | Comments : 0

In the control systems the FPGA systems more often are used as a central computing unit. However, high combination delays of the logic circuits on flexible logics and low maximum tact frequency of the FPGA systems restricts their application. The application of the behavioral hardware description in Verilog HDL for video processing on the hardware platform has been shown. An original algorithm has been proposed for the image features (key points) identifying, which can be used for the object search in the frame by a specified standard. The key points have been determined for the image areas, subjected to affine transformations, i.e. to rotation and scaling. The application of the FPGA systems is stipulated by the necessity of using the proposed algorithms in the systems being built-in with the camera resolution 640×480 pixels at 25 frames per second. The analysis of the frame processing speed by the algorithms, realized on other platforms has been carried out. The quantitative characteristics of the resources have been presented on an example of the Xilinx Spartan-6 FPGA family, their quality has been estimated by testing. The developed algorithm is characterized by the resistance, stability, invariance and its hardware implementation has comparable speed of fulfillment with respect to the most rapid algorithms of a similar class. Due to a small quantity of consumed FPGA resources there is the possibility of scaling and the efficiency improving.

• Counter: 2138 | Comments : 0

While solving the tracking of objects for infrared range images the obtaining of the necessary volume relevant basis for neuron network training is problematic enough. The main obstacles are the absence of the far infrared range images base and the complexity of calibration of cameras of various manufacturers for composing the base. Due to these causes and the complexity of marking the borders of the given range objects using the neuron networks, at the moment, is not expedient. In the paper the principles of object tracking on the infrared range images, based on obtaining the key points using the SIFT, SURF, ORB algorithms, have been considered. The specific features of the given methods have been distinguished, and also, the specifics of far infrared range images and of the objects observed on it, has been emphasized. The analysis of the approaches to preserve the features of tracking an object in transition to a new frame of a video image has been performed, their main advantages and disadvantages have been revealed. Based on the obtained results the modernization of the tracking algorithm using the Jarvis algorithm modification has been proposed. The estimation of the influence on speed of additional processing in the tracking algorithm has been experimentally performed. The proposed approach to tracking an object on the infrared image, composed on the ORB algorithm key points and the application of the modified Jervis algorithm, is invariant to turns and scaling of the sought for object and allows to watch it in conditions of high nonhomogeneity of the background and presence of similar objects. The application of the developed algorithm permits to avoid a considerable loss of speed with a significant increase of the object tracking efficiency.

• Counter: 669 | Comments : 0