Reliable architecture of an embedded stereo vision system for a low cost autonomous vehicle

For the purpose of autonomous satellite grasping, a high-speed, low-cost stereo vision system is required with high accuracy. This type of system must be able to detect an object and estimate its range. Hardware solutions are often chosen over software solutions, which tend to be too slow for high frame-rate applications. Designs utilizing field programmable gate arrays (FPGAs) provide flexibility and are cost effective versus solutions that provide similar performance (i.e., Application Specific Integrated Circuits). This thesis presents the architecture and implementation of a high frame-rate stereo vision system based on an FPGA platform. The system acquires stereo images, performs stereo rectification and generates disparity estimates at frame-rates close to 100 fpSi and on a large-enough FPGA, it can process 200 fps. The implementation presents novelties in performance and in the choice of the algorithm implemented. It achieves superior performance to existing systems that estimate scene depth. Furthermore, it demonstrates equivalent accuracy to software implementations of the dynamic programming maximum likelihood stereo correspondence algorithm.

Download Full-text

Active Stereo Vision for Precise Autonomous Vehicle Control

Electronic Imaging ◽

10.2352/issn.2470-1173.2020.16.avm-257 ◽

2020 ◽

Vol 2020 (16) ◽

pp. 258-1-258-6

Author(s):

Michael Feller ◽

Jae-Sang Hyun ◽

Song Zhang

Keyword(s):

Stereo Vision ◽

Vision System ◽

Low Cost ◽

Autonomous Vehicle ◽

Texture Mapping ◽

Laser Speckle ◽

Projection System ◽

Vision Sensors ◽

Active Stereo ◽

Lateral Error

This paper describes the development of a low-cost, lowpower, accurate sensor designed for precise, feedback control of an autonomous vehicle to a hitch. The solution that has been developed uses an active stereo vision system, combining classical stereo vision with a low cost, low power laser speckle projection system, which solves the correspondence problem experienced by classic stereo vision sensors. A third camera is added to the sensor for texture mapping. A model test of the hitching problem was developed using an RC car and a target to represent a hitch. A control system is implemented to precisely control the vehicle to the hitch. The system can successfully control the vehicle from within 35° of perpendicular to the hitch, to a final position with an overall standard deviation of 3.0 m m of lateral error and 1.5° of angular error.

Download Full-text

Development of a Low Cost and Path-free Autonomous Patrol System Based on Stereo Vision System and Checking Flags

Applied Sciences ◽

10.3390/app10030974 ◽

2020 ◽

Vol 10 (3) ◽

pp. 974

Author(s):

Chien-Wu Lan ◽

Chi-Yao Chang

Keyword(s):

Stereo Vision ◽

Radio Frequency Identification ◽

Vision System ◽

Low Cost ◽

Color Pattern ◽

Depth Information ◽

Rfid Tag ◽

Intruder Detection ◽

Stereo Vision System ◽

Identification Function

Nowadays, security guard patrol services are becoming roboticized. However, high construction prices and complex systems make patrol robots difficult to be popularized. In this research, a simplified autonomous patrolling robot is proposed, which is fabricated by upgrading a wheeling household robot with stereo vision system (SVS), radio frequency identification (RFID) module, and laptop. The robot has four functions: independent patrolling without path planning, checking, intruder detection, and wireless backup. At first, depth information of the environment is analyzed through SVS to find a passable path for independent patrolling. Moreover, the checkpoints made with RFID tag and color pattern are placed in appropriate positions within a guard area. While a color pattern is detected by the SVS, the patrolling robot is guided to approach the pattern and check its RFID tag. For more, the human identification function of SVS is used to detect an intruder. While a skeleton information of the human is analyzed by SVS, the intruder detection function is triggered, then the robot follows the intruder and record the images of the intruder. The recorded images are transmitted to a server through Wi-Fi to realize the remote backup, and users can query the recorded images from the network. Finally, an experiment is made to test the functions of the autonomous patrolling robot successfully.

Download Full-text