Object Detection Through Exploration With A Foveated Visual Field

Abstract

We present a foveated object detector (FOD) as a biologically-inspired alternative to the sliding window (SW) approach which is the dominant method of search in computer vision object detection. Similar to the human visual system, the FOD has higher resolution at the fovea and lower resolution at the visual periphery. Consequently, more computational resources are allocated at the fovea and relatively fewer at the periphery. The FOD processes the entire scene, uses retino-specific object detection classifiers to guide eye movements, aligns its fovea with regions of interest in the input image and integrates observations across multiple fixations. Our approach combines modern object detectors from computer vision with a recent model of peripheral pooling regions found at the V1 layer of the human visual system. We assessed various eye movement strategies on the PASCAL VOC 2007 dataset and show that the FOD performs on par with the SW detector while bringing significant computational cost savings.

An extended version of this manuscript was published in PLOS Computational Biology (October 2017) at https://doi.org/10.1371/journal.pcbi.1005743

References in corpus (4)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
• What makes for effective detection proposals?

Cited by in corpus (9)

• Mind the Pad -- CNNs can Develop Blind Spots
• Emergent Properties of Foveated Perceptual Systems
• Towards Metamerism via Foveated Style Transfer
• Foveated Model Observers for Visual Search in 3D Medical Images
• Foveated image processing for faster object detection and recognition in embedded systems using deep convolutional neural networks
• Can Peripheral Representations Improve Clutter Metrics on Complex Scenes?
• CUDA-Optimized real-time rendering of a Foveated Visual System
• FoveaTer: Foveated Transformer for Image Classification
• The Foes of Neural Network's Data Efficiency Among Unnecessary Input Dimensions