Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices
This work addresses the challenge of real-time video intelligence on resource-constrained edge devices, representing an incremental advance in software/hardware co-optimization for multi-object tracking.
The paper tackles the problem of high-throughput, low-cost, and high-accuracy multi-object tracking on HD video streams for edge devices by proposing a data-model-hardware tri-design framework, achieving 12.5x latency reduction, 20.9x frame rate improvement, 5.83x lower power, and 9.78x better energy efficiency with minimal accuracy drop.
In this paper, we propose a data-model-hardware tri-design framework for high-throughput, low-cost, and high-accuracy multi-object tracking (MOT) on High-Definition (HD) video stream. First, to enable ultra-light video intelligence, we propose temporal frame-filtering and spatial saliency-focusing approaches to reduce the complexity of massive video data. Second, we exploit structure-aware weight sparsity to design a hardware-friendly model compression method. Third, assisted with data and model complexity reduction, we propose a sparsity-aware, scalable, and low-power accelerator design, aiming to deliver real-time performance with high energy efficiency. Different from existing works, we make a solid step towards the synergized software/hardware co-optimization for realistic MOT model implementation. Compared to the state-of-the-art MOT baseline, our tri-design approach can achieve 12.5x latency reduction, 20.9x effective frame rate improvement, 5.83x lower power, and 9.78x better energy efficiency, without much accuracy drop.