An Ultra Fast Low Power Convolutional Neural Network Image Sensor with Pixel-level Computing

• URL: http://arxiv.org/abs/2101.03308v1
• Date: Sat, 9 Jan 2021 07:10:03 GMT
• Title: An Ultra Fast Low Power Convolutional Neural Network Image Sensor with Pixel-level Computing
• Authors: Ruibing Song, Kejie Huang, Zongsheng Wang, Haibin Shen
• Abstract summary: This paper proposes a Processing-In-Pixel (PIP) CMOS sensor architecture, which allows convolution operation before the column readout circuit to significantly improve the image reading speed. In other words, the computational efficiency is 4.75 TOPS/w, which is about 3.6 times as higher as the state-of-the-art.
• Score: 3.41234610095684
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The separation of the data capture and analysis in modern vision systems has led to a massive amount of data transfer between the end devices and cloud computers, resulting in long latency, slow response, and high power consumption. Efficient hardware architectures are under focused development to enable Artificial Intelligence (AI) at the resource-limited end sensing devices. This paper proposes a Processing-In-Pixel (PIP) CMOS sensor architecture, which allows convolution operation before the column readout circuit to significantly improve the image reading speed with much lower power consumption. The simulation results show that the proposed architecture enables convolution operation (kernel size=3*3, stride=2, input channel=3, output channel=64) in a 1080P image sensor array with only 22.62 mW power consumption. In other words, the computational efficiency is 4.75 TOPS/w, which is about 3.6 times as higher as the state-of-the-art.

Related papers

• Data-Driven Pixel Control: Challenges and Prospects [13.158333009169418]
  We study a data-driven system that combines dynamic sensing at the pixel level with computer vision analytics at the video level. Our system achieves a 10X reduction in bandwidth and a 15-30X improvement in Energy-Delay Product (EDP) when activating only 30% of pixels.
  arXiv  Detail & Related papers  (2024-08-08T21:49:19Z)
• Efficient and accurate neural field reconstruction using resistive memory [52.68088466453264]
  Traditional signal reconstruction methods on digital computers face both software and hardware challenges. We propose a systematic approach with software-hardware co-optimizations for signal reconstruction from sparse inputs. This work advances the AI-driven signal restoration technology and paves the way for future efficient and robust medical AI and 3D vision applications.
  arXiv  Detail & Related papers  (2024-04-15T09:33:09Z)
• Random resistive memory-based deep extreme point learning machine for unified visual processing [67.51600474104171]
  We propose a novel hardware-software co-design, random resistive memory-based deep extreme point learning machine (DEPLM) Our co-design system achieves huge energy efficiency improvements and training cost reduction when compared to conventional systems.
  arXiv  Detail & Related papers  (2023-12-14T09:46:16Z)
• INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing [66.00729477511219]
  Given a function represented as a computation graph, traditional architectures face challenges in efficiently computing its nth-order gradient. We introduce INR-Arch, a framework that transforms the computation graph of an nth-order gradient into a hardware-optimized dataflow architecture. We present results that demonstrate 1.8-4.8x and 1.5-3.6x speedup compared to CPU and GPU baselines respectively.
  arXiv  Detail & Related papers  (2023-08-11T04:24:39Z)
• PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors [42.18718773182277]
  Conventional image sensors digitize high-resolution images at fast frame rates, producing a large amount of data that needs to be transmitted off the sensor for further processing. We develop an efficient recurrent neural network architecture, processing PixelRNN, that encodes-temporal features on the sensor using purely binary operations. PixelRNN reduces the amount data to be transmitted off the sensor by a factor of 64x compared to conventional systems while offering competitive accuracy for hand gesture recognition and lip reading tasks.
  arXiv  Detail & Related papers  (2023-04-11T18:16:47Z)
• Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices [90.30316433184414]
  We propose a data-model-hardware tri-design framework for high- throughput, low-cost, and high-accuracy MOT on HD video stream. 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.
  arXiv  Detail & Related papers  (2022-10-16T16:21:40Z)
• FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation [81.76975488010213]
  Dense optical flow estimation plays a key role in many robotic vision tasks. Current networks often occupy large number of parameters and require heavy computation costs. Our proposed FastFlowNet works in the well-known coarse-to-fine manner with following innovations.
  arXiv  Detail & Related papers  (2021-03-08T03:09:37Z)
• AnalogNet: Convolutional Neural Network Inference on Analog Focal Plane Sensor Processors [0.0]
  We present a high-speed, energy-efficient Convolutional Neural Network (CNN) architecture utilising the capabilities of a unique class of devices known as analog Plane Sensor Processors (FPSP) Unlike traditional vision systems, where the sensor array sends collected data to a separate processor for processing, FPSPs allow data to be processed on the imaging device itself. Our proposed architecture, coined AnalogNet, reaches a testing accuracy of 96.9% on the MNIST handwritten digits recognition task, at a speed of 2260 FPS, for a cost of 0.7 mJ per frame.
  arXiv  Detail & Related papers  (2020-06-02T16:44:43Z)
• Fully Embedding Fast Convolutional Networks on Pixel Processor Arrays [16.531637803429277]
  We present a novel method of CNN inference for pixel processor array ( PPA) vision sensors. Our approach can perform convolutional layers, max pooling, ReLu, and a final fully connected layer entirely upon the PPA sensor. This is the first work demonstrating CNN inference conducted entirely upon the processor array of a PPA vision sensor device, requiring no external processing.
  arXiv  Detail & Related papers  (2020-04-27T01:00:35Z)
• Near-chip Dynamic Vision Filtering for Low-Bandwidth Pedestrian Detection [99.94079901071163]
  This paper presents a novel end-to-end system for pedestrian detection using Dynamic Vision Sensors (DVSs) We target applications where multiple sensors transmit data to a local processing unit, which executes a detection algorithm. Our detector is able to perform a detection every 450 ms, with an overall testing F1 score of 83%.
  arXiv  Detail & Related papers  (2020-04-03T17:36:26Z)
• A Machine Learning Imaging Core using Separable FIR-IIR Filters [2.099922236065961]
  We use a fully trainable, fixed-topology neural network to build a model that can perform a wide variety of image processing tasks. Our proposed Machine Learning Imaging Core, dubbed MagIC, uses a silicon area of 3mm2. Each MagIC core consumes 56mW (215 mW max power) at 500MHz and achieves an energy-efficient throughput of 23TOPS/W/mm2.
  arXiv  Detail & Related papers  (2020-01-02T21:24:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.