Retina-inspired Object Motion Segmentation

• URL: http://arxiv.org/abs/2408.09454v1
• Date: Sun, 18 Aug 2024 12:28:26 GMT
• Title: Retina-inspired Object Motion Segmentation
• Authors: Victoria Clerico, Shay Snyder, Arya Lohia, Md Abdullah-Al Kaiser, Gregory Schwartz, Akhilesh Jaiswal, Maryam Parsa,
• Abstract summary: Dynamic Vision Sensors (DVS) have emerged as a revolutionary technology with a high temporal resolution that far surpasses RGB cameras. This paper introduces a bio-inspired computer vision method that dramatically reduces the number of parameters by a factor of 1000 compared to prior works.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dynamic Vision Sensors (DVS) have emerged as a revolutionary technology with a high temporal resolution that far surpasses RGB cameras. DVS technology draws biological inspiration from photoreceptors and the initial retinal synapse. Our research showcases the potential of additional retinal functionalities to extract visual features. We provide a domain-agnostic and efficient algorithm for ego-motion compensation based on Object Motion Sensitivity (OMS), one of the multiple robust features computed within the mammalian retina. We develop a framework based on experimental neuroscience that translates OMS' biological circuitry to a low-overhead algorithm. OMS processes DVS data from dynamic scenes to perform pixel-wise object motion segmentation. Using a real and a synthetic dataset, we highlight OMS' ability to differentiate object motion from ego-motion, bypassing the need for deep networks. This paper introduces a bio-inspired computer vision method that dramatically reduces the number of parameters by a factor of 1000 compared to prior works. Our work paves the way for robust, high-speed, and low-bandwidth decision-making for in-sensor computations.

Related papers

• Neural Ganglion Sensors: Learning Task-specific Event Cameras Inspired by the Neural Circuit of the Human Retina [35.26330639016294]
  We introduce Neural Ganglion Sensors, an extension of traditional event cameras. Our results demonstrate that our biologically inspired sensing improves performance relative to conventional event cameras. These findings highlight the promise of RGC-inspired event sensors for edge devices and other low-power, real-time applications.
  arXiv  Detail & Related papers  (2025-04-18T04:22:58Z)
• Wandering around: A bioinspired approach to visual attention through object motion sensitivity [40.966228784674115]
  Active vision enables dynamic visual perception, offering an alternative to static feedforward architectures in computer vision. Event-based cameras, inspired by the mammalian retina, enhance this capability by capturing asynchronous scene changes. To distinguish moving objects while the event-based camera is in motion the agent requires an object motion segmentation mechanism. This work presents a Convolutional Neural Network bio-inspired attention system for selective attention through object motion sensitivity.
  arXiv  Detail & Related papers  (2025-02-10T18:16:30Z)
• Hardware-Algorithm Re-engineering of Retinal Circuit for Intelligent Object Motion Segmentation [0.0]
  We focus on a fundamental visual feature within the mammalian retina, Object Motion Sensitivity (OMS) We present novel CMOS circuits that implement OMS functionality inside image sensors. We verify the functionality and re-configurability of the proposed CMOS circuit designs through Cadence simulations in 180nm technology.
  arXiv  Detail & Related papers  (2024-07-31T20:35:11Z)
• SaccadeDet: A Novel Dual-Stage Architecture for Rapid and Accurate Detection in Gigapixel Images [50.742420049839474]
  'SaccadeDet' is an innovative architecture for gigapixel-level object detection, inspired by the human eye saccadic movement. Our approach, evaluated on the PANDA dataset, achieves an 8x speed increase over the state-of-the-art methods. It also demonstrates significant potential in gigapixel-level pathology analysis through its application to Whole Slide Imaging.
  arXiv  Detail & Related papers  (2024-07-25T11:22:54Z)
• TSOM: Small Object Motion Detection Neural Network Inspired by Avian Visual Circuit [4.640328175695991]
  The Retina-OT-Rt visual circuit is highly sensitive to capturing the motion information of small objects from high altitudes. We propose a novel tectum small object motion detection neural network (TSOM) The TSOM is biologically interpretable and effective in extracting reliable small object motion features from complex high-altitude backgrounds.
  arXiv  Detail & Related papers  (2024-04-01T01:49:08Z)
• Neuromorphic Synergy for Video Binarization [54.195375576583864]
  Bimodal objects serve as a visual form to embed information that can be easily recognized by vision systems. Neuromorphic cameras offer new capabilities for alleviating motion blur, but it is non-trivial to first de-blur and then binarize the images in a real-time manner. We propose an event-based binary reconstruction method that leverages the prior knowledge of the bimodal target's properties to perform inference independently in both event space and image space. We also develop an efficient integration method to propagate this binary image to high frame rate binary video.
  arXiv  Detail & Related papers  (2024-02-20T01:43:51Z)
• Neural feels with neural fields: Visuo-tactile perception for in-hand manipulation [57.60490773016364]
  We combine vision and touch sensing on a multi-fingered hand to estimate an object's pose and shape during in-hand manipulation. Our method, NeuralFeels, encodes object geometry by learning a neural field online and jointly tracks it by optimizing a pose graph problem. Our results demonstrate that touch, at the very least, refines and, at the very best, disambiguates visual estimates during in-hand manipulation.
  arXiv  Detail & Related papers  (2023-12-20T22:36:37Z)
• 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)
• EventTransAct: A video transformer-based framework for Event-camera based action recognition [52.537021302246664]
  Event cameras offer new opportunities compared to standard action recognition in RGB videos. In this study, we employ a computationally efficient model, namely the video transformer network (VTN), which initially acquires spatial embeddings per event-frame. In order to better adopt the VTN for the sparse and fine-grained nature of event data, we design Event-Contrastive Loss ($mathcalL_EC$) and event-specific augmentations.
  arXiv  Detail & Related papers  (2023-08-25T23:51:07Z)
• Modelling Human Visual Motion Processing with Trainable Motion Energy Sensing and a Self-attention Network [1.9458156037869137]
  We propose an image-computable model of human motion perception by bridging the gap between biological and computer vision models. This model architecture aims to capture the computations in V1-MT, the core structure for motion perception in the biological visual system. In silico neurophysiology reveals that our model's unit responses are similar to mammalian neural recordings regarding motion pooling and speed tuning.
  arXiv  Detail & Related papers  (2023-05-16T04:16:07Z)
• Object Motion Sensitivity: A Bio-inspired Solution to the Ego-motion Problem for Event-based Cameras [0.0]
  We highlight the capability of the second generation of neuromorphic image sensors, Integrated Retinal Functionality in CMOS Image Sensors (IRIS) IRIS aims to mimic full retinal computations from photoreceptors to output of the retina for targeted feature-extraction. Our results show that OMS can accomplish standard computer vision tasks with similar efficiency to conventional RGB and DVS solutions but offers drastic bandwidth reduction.
  arXiv  Detail & Related papers  (2023-03-24T16:22:06Z)
• Robotic Navigation Autonomy for Subretinal Injection via Intelligent Real-Time Virtual iOCT Volume Slicing [88.99939660183881]
  We propose a framework for autonomous robotic navigation for subretinal injection. Our method consists of an instrument pose estimation method, an online registration between the robotic and the i OCT system, and trajectory planning tailored for navigation to an injection target. Our experiments on ex-vivo porcine eyes demonstrate the precision and repeatability of the method.
  arXiv  Detail & Related papers  (2023-01-17T21:41:21Z)
• Neuromorphic Computing and Sensing in Space [69.34740063574921]
  Neuromorphic computer chips are designed to mimic the architecture of a biological brain. The emphasis on low power and energy efficiency of neuromorphic devices is a perfect match for space applications.
  arXiv  Detail & Related papers  (2022-12-10T07:46:29Z)
• Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition [56.91538445510214]
  We present a learning algorithm for human activity recognition in videos. Our approach is designed for UAV videos, which are mainly acquired from obliquely placed dynamic cameras. We conduct extensive experiments on the UAV Human dataset and the NEC Drone dataset.
  arXiv  Detail & Related papers  (2022-09-15T22:16:52Z)
• Visual Odometry with Neuromorphic Resonator Networks [9.903137966539898]
  Visual Odometry (VO) is a method to estimate self-motion of a mobile robot using visual sensors. Neuromorphic hardware offers low-power solutions to many vision and AI problems. We present a modular neuromorphic algorithm that achieves state-of-the-art performance on two-dimensional VO tasks.
  arXiv  Detail & Related papers  (2022-09-05T14:57:03Z)
• CNN-based Omnidirectional Object Detection for HermesBot Autonomous Delivery Robot with Preliminary Frame Classification [53.56290185900837]
  We propose an algorithm for optimizing a neural network for object detection using preliminary binary frame classification. An autonomous mobile robot with 6 rolling-shutter cameras on the perimeter providing a 360-degree field of view was used as the experimental setup.
  arXiv  Detail & Related papers  (2021-10-22T15:05:37Z)
• Deep Homography Estimation in Dynamic Surgical Scenes for Laparoscopic Camera Motion Extraction [6.56651216023737]
  We introduce a method that allows to extract a laparoscope holder's actions from videos of laparoscopic interventions. We synthetically add camera motion to a newly acquired dataset of camera motion free da Vinci surgery image sequences. We find our method transfers from our camera motion free da Vinci surgery dataset to videos of laparoscopic interventions, outperforming classical homography estimation approaches in both, precision by 41%, and runtime on a CPU by 43%.
  arXiv  Detail & Related papers  (2021-09-30T13:05:37Z)
• Optical Flow Estimation from a Single Motion-blurred Image [66.2061278123057]
  Motion blur in an image may have practical interests in fundamental computer vision problems. We propose a novel framework to estimate optical flow from a single motion-blurred image in an end-to-end manner.
  arXiv  Detail & Related papers  (2021-03-04T12:45:18Z)
• Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition [131.6328804788164]
  We propose a framework, named Semantics-aware Adaptive Knowledge Distillation Networks (SAKDN), to enhance action recognition in vision-sensor modality (videos) The SAKDN uses multiple wearable-sensors as teacher modalities and uses RGB videos as student modality.
  arXiv  Detail & Related papers  (2020-09-01T03:38:31Z)

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.