Design of A Miniature Near-infrared Laser Range-gated Real-time Video Processing System

With the rapid development of aerial UAV (Unmanned Aerial Vehicle), the design of real-time data acquisition and transmission system for the video signal has a new applied field. It is different from traditional video acquisition and processing system, aerial video signal has the problems of screen jitter and spatial interference. The processing algorithm of aerial UAV airborne video signal is put forward in the paper, and the platform of high speed procession is constructed based on chip TMS320DM642, and get a good effect.

Download Full-text

FPGA-Based Stereo-Vision System Mimicking Human Binocular Vision

10.32920/ryerson.14646192 ◽

2021 ◽

Author(s):

Gvarami Labartkava

Keyword(s):

Real Time ◽

Binocular Vision ◽

Video Processing ◽

High Performance ◽

Moving Objects ◽

Peripheral Vision ◽

Vision System ◽

Processing System ◽

Object Motion ◽

Human Vision

Human vision is a complex system which involves processing frames and retrieving information in a real-time with optimization of the memory, energy and computational resources usage. It can be widely utilized in many real-world applications from security systems to space missions. The research investigates fundamental principles of human vision and accordingly develops a FPGA-based video processing system with binocular vision, capable of high performance and real-time tracking of moving objects in 3D space. The undertaken research and implementation consist of: 1. Analysis of concepts and methods of human vision system; 2. Development stereo and peripheral vision prototype of a system-on-programmable chip (SoPC) for multi-object motion detection and tracking; 3. Verification, test run and analysis of the experimental results gained on the prototype and associated with the performance constraints; The implemented system proposes a platform for real-time applications which are limited in current approaches.

Download Full-text

Energy-Efficient NoC-Based Systems for Real-Time Multimedia Applications using Approximate Computing

10.5753/ctd.2021.15750 ◽

2021 ◽

Author(s):

Wagner I. Penny ◽

Daniel M. Palomino ◽

Marcelo S. Porto ◽

Bruno Zatt

Keyword(s):

Real Time ◽

Video Processing ◽

Energy Efficient ◽

Processing System ◽

Schedulability Analysis ◽

Multimedia Applications ◽

Timing Constraints ◽

Approximate Computing ◽

Processing Elements ◽

Fractional Motion Estimation

This work presents an energy-efficient NoC-based system for real-time multimedia applications employing approximate computing. The proposed video processing system, called SApp-NoC, is efficient in both energy and quality (QoS), employing a scalable NoC architecture composed of processing elements designed to accelerate the HEVC Fractional Motion Estimation (FME). Two solutions are proposed: HSApp-NoC (Heuristc-based SApp-NoC), and MLSApp-NoC (Machine Learning-based SApp-NoC). When compared to a precise solution processing 4K videos at 120 fps, HSApp-NoC and MLSApp-NoC reduce about 48.19% and 31.81% the energy consumption, at small quality reduction of 2.74% and 1.09%, respectively. Furthermore, a set of schedulability analysis is also proposed in order to guarantee the meeting of timing constraints at typical workload scenarios.

Download Full-text