ABSTRACT
Latest vision tasks trend to be the real-time processing with high throughput frame rate and low latency. High spatiotemporal resolution imagers continue to spring up but only a few of them can be used in real applications owing to the excessive computational burden and lacking of suitable architecture. This paper presents a solution for target detection task in imager-driven processing mode (IMP), which takes shorter time in processing than the time gap between frames, even if the ulreafast imager run at full frame rate. High throughput pixel stream outputted from imager is analyzed base on multi features in a fully pipelined and bufferless architecture in FPGA. A pyramid shape model consisting of 2-D Processing Element (PE) array is proposed to search the connected regions of target candidates distributed at different time slices, and extract corresponding features when the stream pass through. A Label based 1-D PE Array collects the feature flow generated by the pyramid according to their labels, and output the feature vector of each target candidate in real time. The proposed model has been tested in simulation and experiments for target detection with 0.8Gpixel/sec (2320×1726 with 192FPS) data stream input, and the latency is less than 1 microsecond.
- Friston, Sebastian, et al. "Construction and evaluation of an ultra low latency frameless renderer for VR." IEEE transactions on visualization and computer graphics 22.4 (2016): 1377--1386. Google ScholarDigital Library
- Van der Wal, Gooitzen, et al. "FPGA acceleration for feature based processing applications." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2015.Google Scholar
- Liu, Shaoshan, et al. "Computer Architectures for Autonomous Driving." Computer 50.8 (2017): 18--25.Google Scholar
- Petr Vaí?ek,Jan Faigl, and Diar Masri. "Low-latency image processing for vision-based navigation systems." Robotics and Automation (ICRA), 2016 IEEE International Conference on. IEEE, 2016.Google Scholar
- Kitamura, K. et.al., A 33-Megapixel 120-Frames-Per-Second 2.5-Watt CMOS Image Sensor With Column-Parallel Two-Stage Cyclic Analog-to-Digital Converters. Ieee Transactions on Electron Devices, 59, 12 (Dec 2012), 3426--3433.Google ScholarCross Ref
- Tochigi, Y. et.al., A Global-Shutter CMOS Image Sensor With Readout Speed of 1-Tpixel/s Burst and 780-Mpixel/s Continuous. Ieee Journal of Solid-State Circuits, 48, 1 (Jan 2013), 329--338.Google ScholarCross Ref
- Okura, S. et.al., A 3.7 M-Pixel 1300-fps CMOS Image Sensor With 5.0 G-Pixel/s High-Speed Readout Circuit. Ieee Journal of Solid-State Circuits, 50, 4 (Apr 2015), 1016--1024.Google ScholarCross Ref
- Brenot, Francois, Philippe Fillatreau, and Jonathan Piat. "FPGA based accelerator for visual features detection." Electronics, Control, Measurement, Signals and their Application to Mechatronics (ECMSM), 2015 IEEE International Workshop of. IEEE, 2015.Google Scholar
- Hahnle, Michael, et al. "FPGA-based real-time pedestrian detection on high-resolution images." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2013. Google ScholarDigital Library
- Chen, Yu-Hsin, Joel Emer, and Vivienne Sze. "Eyeriss: A spatial architecture for energy-efficient dataflow for convolutional neural networks." Computer Architecture (ISCA), 2016 ACM/IEEE 43rd Annual International Symposium on. IEEE, 2016. Google ScholarDigital Library
- Allied Vision, Technical Manual AVT Bonito, https://www.alliedvision.com/fileadmin/content/documents/products/cameras/Bonito/techman/Bonito_TechMan.pdfGoogle Scholar
- Comaniciu, D., Ramesh, V. and Meer, P. Kernel-based object tracking. Ieee Transactions on Pattern Analysis and Machine Intelligence, 25, 5 (May 2003), 564--577. Google ScholarDigital Library
- S. Arulampalam, S. Maskell, N. Gordon, T. Clapp, A tutorial on particle filters for on-line non-linear/non-Gaussian bayesian tracking{J}, IEEE Trans. Signal Process. 50 (2) (2002) 174--188. Google ScholarDigital Library
- Ghoniemy S S A. GPU-based Real-Time Multiple Moving Objects Tracking using Integrated Spatial Region Graph for Video Surveillance{J}.Google Scholar
- Mahmoudi S A, Manneback P. Multi-GPU based event detection and localization using high definition videos{C}//Multimedia Computing and Systems (ICMCS), 2014 International Conference on. IEEE, 2014: 81--86.Google Scholar
- ZHOU P, LIU Y, WANG Y T. Pipeline Architecture and Parallel Computation-Based Real-Time Stereovision Tracking System for Surgical Navigation {J}. Ieee Transactions on Instrumentation and Mea surement, 2010, 59(5): 1240--50.Google Scholar
- Tao, Wenbing, Hai Jin, and Yimin Zhang. Color image segmentation based on mean shift and normalized cuts. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 37.5 (2007): 1382--1389. Google ScholarDigital Library
- Elgammal, A., Duraiswami, R., Harwood, D. and Davis, L. S. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proceedings of the Ieee, 90, 7 (Jul 2002), 1151--1163.Google ScholarCross Ref
- Gangodkar, D., Kumar, P. and Mittal, A. Robust Segmentation of Moving Vehicles Under Complex Outdoor Conditions. Ieee Transactions on Intelligent Transportation Systems, 13, 4 (Dec 2012), 1738--1752. Google ScholarDigital Library
- Grana, C., Borghesani, D. and Cucchiara, R. Optimized Block-Based Connected Components Labeling With Decision Trees. Ieee Transactions on Image Processing, 19, 6 (Jun 2010), 1596--1609. Google ScholarDigital Library
- https://pan.baidu.com/s/1kU6VFkbGoogle Scholar
- ftp://ftp.cs.rdg.ac.uk/pub/PETS2001/Google Scholar
- Schwenk, Kurt, and F. Huber. "Connected Component Labeling algorithm for very complex and high-resolution images on an FPGA platform." High-Performance Computing in Remote Sensing V, 2015.Google Scholar
- YASUAKI ITO, and KOJI NAKANO. "LOW-LATENCY CONNECTED COMPONENT LABELING USING AN FPGA." International Journal of Foundations of Computer Science 21.03(2010):405--425.Google Scholar
- Szkudlarek, M, and M. Pietruszka. "Fast GPU and CPU computing for head position estimation." Computer Science and Information Systems IEEE, 2015:231--240.Google Scholar
Index Terms
- Performance Comparison of Multiples and Target Detection with Imager-driven Processing Mode for Ultrafast-Imager: (Abstract Only)
Recommendations
A real-time unsupervised background extraction-based target detection method for hyperspectral imagery
Target detection is an important technique in hyperspectral image analysis. The high dimensionality of hyperspectral data provides the possibility of deeply mining the information hiding in spectra, and many targets that cannot be visualized by ...
Research on Target Detection Method Based on Improved YOLOv5
Web Information Systems and ApplicationsAbstractAt present, various target detection algorithms are used in detection and classification. It is a problem to improve the accuracy and speed of target detection by using deep learning and neural network model to train the parameters of the data ...
Detection-guided multi-target Bayesian filter
Multi-target Bayesian filter in the framework of finite set statistics (FISST) and its approximations, including probability hypothesis density (PHD) filter and cardinalized probability hypothesis density (CPHD) filter, are elegant methods for multi-...
Comments