• A neuro-inspired visual tracking method based on programmable system-on-chip platform

      Yang, Shufan; Wong-Lin, KongFatt; Andrew, James; Mak, Terrence; McGinnity, T. Martin (Springer, 2017-01-20)
      Using programmable system-on-chip to implement computer vision functions poses many challenges due to highly constrained resources in cost, size and power consumption. In this work, we propose a new neuro-inspired image processing model and implemented it on a system-on-chip Xilinx Z702c board. With the attractor neural network model to store the object’s contour information, we eliminate the computationally expensive steps in the curve evolution re-initialisation at every new iteration or frame. Our experimental results demonstrate that this integrated approach achieves accurate and robust object tracking, when they are partially or completely occluded in the scenes. Importantly, the system is able to process 640 by 480 videos in real-time stream with 30 frames per second using only one low-power Xilinx Zynq-7000 system-on-chip platform. This proof-of-concept work has demonstrated the advantage of incorporating neuro-inspired features in solving image processing problems during occlusion.
    • A Single Chip System for Sensor Data Fusion Based on a Drift-diffusion Model

      Yang, Shufan; Wong-Lin, Kongfatt; Rano, Inaki; Lindsay, Anthony (IEEE, 2017-09-07)
      Current multisensory system face data communication overhead in integrating disparate sensor data to build a coherent and accurate global phenomenon. We present here a novel hardware and software co-design platform for a heterogeneous data fusion solution based on a perceptual decision making approach (the drift-diffusion model). It provides a convenient infrastructure for sensor data acquisition and data integration and only uses a single chip Xilinx ZYNQ-7000 XC7Z020 AP SOC. A case study of controlling the moving speed of a single ground-based robot, according to physiological states of the operator based on heart rates, is conducted and demonstrates the possibility of integrated sensor data fusion architecture. The results of our DDM-based data integration shows a better correlation coefficient with the raw ECG signal compare with a simply piecewise approach.
    • An intelligible implementation of FastSLAM2.0 on a low-power embedded architecture

      Jiménez Serrata, Albert A.; Yang, Shufan; Li, Renfa (Springer, 2017-03-02)
      The simultaneous localisation and mapping (SLAM) algorithm has drawn increasing interests in autonomous robotic systems. However, SLAM has not been widely explored in embedded system design spaces yet due to the limitation of processing recourses in embedded systems. Especially when landmarks are not identifiable, the amount of computer processing will dramatically increase due to unknown data association. In this work, we propose an intelligible SLAM solution for an embedded processing platform to reduce computer processing time using a low-variance resampling technique. Our prototype includes a low-cost pixy camera, a Robot kit with L298N motor board and Raspberry Pi V2.0. Our prototype is able to recognise artificial landmarks in a real environment with an average 75% of identified landmarks in corner detection and corridor detection with only average 1.14 W.