Abstract
Abstract Background In a construction site, the safety of workers can be better secured if vehicle or robot can be properly maneuvered by using image-based gesture guidance. This kind of semi-automatic motion control is based on the features extracted in colors, outlines, textures, and motion intentions. Among these features, detecting worker’s skin color on face and hands could serve as an essential method for enabling robot to determine the region of interest (ROI). However, the performance of skin detection is usually unreliable due to interferences from reflections and shadows. Although many efficient skin color detection methods had been developed in past years, those are mostly based on complicated learning and statistical processes and are unsuitable for embedded systems. The exploration of a concise and efficient skin color detector, therefore, becomes a challenge for applications in mobile robots. Method In this paper, we propose a novel adaptive skin detector on face and hands as a fundamental capability of a gesture tracking system. This approach enhances the detection performance of traditional HSV color space but only requires a low computing power. For the design criteria of small size, low-power, low-cost, and minimum computing resource usages on mobile robots, the entire detecting system is built on single field-programmable-gate-array (FPGA) chip. Meanwhile, besides the contributions of adaptive algorithms and FPGA chip designs, the proposed skin detector also employs a touch screen to designate expected skin color of worker as the human-robot interaction (HRI) in real-time. Results The chip design of the FPGA is based on hardware circuits in register-transfer-level (RTL) for real-time image processing. A reasonable amount of hardware resource usages of FPGA have consumed 8% of logic elements (LEs) and 1.4% for embedded random access memory (RAM). Demonstrations with various pictures had indicated that sufficient ROI can be efficiently identified by using the proposed adaptive skin color detector. Conclusions According to our experimental results, the proposed adaptive skin detection can work well for non-ideal illumination. It has demonstrated the reliability and feasibility on supporting the embedded robotic control in the future.
Highlights
In a construction site, the safety of workers can be better secured if vehicle or robot can be properly maneuvered by using image-based gesture guidance
The chip design of the FPGA is based on hardware circuits in register-transfer-level (RTL) for real-time image processing
We propose an adaptive skin color detection strategy by using single FPGA chip
Summary
To designate expected skin color of worker and examines detection performance. The digital camera module is vertically installed on a slot of the FPGA platform. In these test scenarios, the skin color detections by using traditional RGB and HSV thresholds were conducted to compare with our TCH algorithm using constant skin color map. The lights in laboratory were nearly turned off in this test scenario It can be seen the RGB and HSV thresholds could surprisingly detect skin region of the subject, and the silhouette of HSV threshold was sufficient for recognition on the face and palm. Discussions The salient features of the proposed skin color detection system involve simple calibration processes, moderate hardware resource usage on chips, and efficient adaptability without complicated training algorithms. The coarse binary picture quality seems not affecting detection rate, the authors will determine how to improve processing speed with refined hardware circuits in the future, and a real-time and simplified pixel-based noise filter from our previous work may be implemented (Yu et al 2011)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
