scholarly journals Flying Robot with Biologically Inspired Vision

2001 ◽  
Vol 13 (6) ◽  
pp. 621-624 ◽  
Author(s):  
Michinori Ichikawa ◽  
◽  
Hitoshi Yamada ◽  
Johane Takeuchi

An autonomous helicopter controlled by biologically inspired vision detects the displacement of altitude with real-time video processing, using has 2 CCD video cameras to see landscape objects and processing circuitry with an FPGA. Each image is divided into 800 areas for edge detection, used to detect displacement. Each of these small areas works as an ommatidium, i.e., the compound eye of an insect. In a typical indoor setting (objects such as desks, walls, etc.) visual feedback was not sufficient to realize stable hovering, but additional external feedback helps keep the unstable robot in more stable flight.

2018 ◽  
pp. 1133-1154
Author(s):  
Ahmed Abouelfarag ◽  
Marwa Ali Elshenawy ◽  
Esraa Alaaeldin Khattab

Recently, computer vision is playing an important role in many essential human-computer interactive applications, these applications are subject to a “real-time” constraint, and therefore it requires a fast and reliable computational system. Edge Detection is the most used approach for segmenting images based on changes in intensity. There are various kernels used to perform edge detection, such as: Sobel, Robert, and Prewitt, upon which, the most commonly used is Sobel. In this research a novel type of operator cells that perform addition is introduced to achieve computational acceleration. The novel operator cells have been employed in the chosen FPGA Zedboard which is well-suited for real-time image and video processing. Accelerating the Sobel edge detection technique is exploited using different tools such as the High-Level Synthesis tools provided by Vivado. This enhancement shows a significant improvement as it decreases the computational time by 26% compared to the conventional adder cells.


Author(s):  
Ahmed Abouelfarag ◽  
Marwa Ali Elshenawy ◽  
Esraa Alaaeldin Khattab

Recently, computer vision is playing an important role in many essential human-computer interactive applications, these applications are subject to a “real-time” constraint, and therefore it requires a fast and reliable computational system. Edge Detection is the most used approach for segmenting images based on changes in intensity. There are various kernels used to perform edge detection, such as: Sobel, Robert, and Prewitt, upon which, the most commonly used is Sobel. In this research a novel type of operator cells that perform addition is introduced to achieve computational acceleration. The novel operator cells have been employed in the chosen FPGA Zedboard which is well-suited for real-time image and video processing. Accelerating the Sobel edge detection technique is exploited using different tools such as the High-Level Synthesis tools provided by Vivado. This enhancement shows a significant improvement as it decreases the computational time by 26% compared to the conventional adder cells.


2020 ◽  
Vol 8 (5) ◽  
pp. 2466-2468

Edge detection is a fundamental operation in many image and video processing applications. It is used in various fields like industries, aerospace, surveillance, medical fields, traffic monitoring system, lane detection, driverless vehicles, crack detection in roads and several other applications. Most of the edge detection algorithms are software based but in real time applications these are not efficient hence in this paper we have explored about Hardware platform. The reason for selecting Sobel edge detection operator is it incorporates both the edge detection and a smoothing operator to provide good edge detection capability in noisy environment. This design uses Verilog HDL language for design and Vivado is used for simulation.


2002 ◽  
Author(s):  
Wei Liu ◽  
Zeying Chi ◽  
Wenjian Chen

Sign in / Sign up

Export Citation Format

Share Document