DeepAI AI Chat
Log In Sign Up

VisionISP: Repurposing the Image Signal Processor for Computer Vision Applications

by   Chyuan-Tyng Wu, et al.

Traditional image signal processors (ISPs) are primarily designed and optimized to improve the image quality perceived by humans. However, optimal perceptual image quality does not always translate into optimal performance for computer vision applications. We propose a set of methods, which we collectively call VisionISP, to repurpose the ISP for machine consumption. VisionISP significantly reduces data transmission needs by reducing the bit-depth and resolution while preserving the relevant information. The blocks in VisionISP are simple, content-aware, and trainable. Experimental results show that VisionISP boosts the performance of a subsequent computer vision system trained to detect objects in an autonomous driving setting. The results demonstrate the potential and the practicality of VisionISP for computer vision applications.


Automatic ISP image quality tuning using non-linear optimization

Image Signal Processor (ISP) comprises of various blocks to reconstruct ...

DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition

Image signal processor (ISP) plays an important role not only for human ...

Utility-Based Control for Computer Vision

Several key issues arise in implementing computer vision recognition of ...

Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop

No-reference image quality assessment (NR-IQA) aims to quantify how huma...

Image Quality Is Not All You Want: Task-Driven Lens Design for Image Classification

In computer vision, it has long been taken for granted that high-quality...

Use of Computer Vision to Detect Tangles in Tangled Objects

Untangling of structures like ropes and wires by autonomous robots can b...

Does computer vision matter for action?

Computer vision produces representations of scene content. Much computer...