EBBINNOT: A Hardware Efficient Hybrid Event-Frame Tracker for Stationary Dynamic Vision Sensors
Authors:
- Vivek MohanVMVivek Mohan
- Deepak SinglaDSDeepak Singla
- Tarun PulluriTPTarun Pulluri
- Andres UssaAUAndres Ussa
- Pradeep Kumar GopalakrishnanPGPradeep Kumar Gopalakrishnan
- Pao-Sheng SunPSPao-Sheng Sun
- Bharath RameshBRBharath Ramesh
- Arindam BasuABArindam Basu
Preprint
Abstract
As an alternative sensing paradigm, dynamic vision sensors (DVS) have been recently explored to tackle scenarios where conventional sensors result in high data rate and processing time. This paper presents a hybrid event-frame approach for detecting and tracking objects recorded by a stationary neuromorphic sensor, thereby exploiting the sparse DVS output in a low-power setting for traffic monitoring. Specifically, we propose a hardware efficient processing pipeline that optimizes memory and computational needs that enable long-term battery powered usage for IoT applications. To exploit the background removal property of a static DVS, we propose an event-based binary image creation that signals presence or absence of events in a frame duration. This reduces memory requirement and enables usage of simple algorithms like median filtering and connected component labeling for denoise and region proposal respectively. To overcome the fragmentation issue, a YOLO inspired neural network based detector and classifier to merge fragmented region proposals has been proposed. Finally, a new overlap based tracker was implemented, exploiting overlap between detections and tracks is proposed with heuristics to overcome occlusion. The proposed pipeline is evaluated with more than 5 hours of traffic recording spanning three different locations on two different neuromorphic sensors (DVS and CeleX) and demonstrate similar performance. Compared to existing event-based feature trackers, our method provides similar accuracy while needing approx 6 times less computes. To the best of our knowledge, this is the first time a stationary DVS based traffic monitoring solution is extensively compared to simultaneously recorded RGB frame-based methods while showing tremendous promise by outperforming state-of-the-art deep learning solutions.Keywords
All Related Versions
This publication has 38 references indexed in Scilit:
- Object tracking on event cameras with offline–online learningCAAI Transactions on Intelligence Technology, 2020
- Towards artificial general intelligence with hybrid Tianjic chip architectureNature, 2019
- Multiple Object Tracking With Attention to Appearance, Structure, Motion and SizeIEEE Access, 2019
- YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers2018
- The connected-component labeling problem: A review of state-of-the-art algorithmsPattern Recognition, 2017
- Superior colliculus encodes visual saliency before the primary visual cortexProceedings of the National Academy of Sciences, 2017
- Learning Non-maximum Suppression2017
- How is visual salience computed in the brain? Insights from behaviour, neurobiology and modellingPhilosophical Transactions of the Royal Society B: Biological Sciences, 2017
- You Only Look Once: Unified, Real-Time Object Detection2016
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998