A Robust Illumination-Invariant Camera System for Agricultural Applications

TL;DR

This paper introduces a robust active lighting camera system that produces consistent images in varying outdoor lighting, significantly reducing training data needs for deep learning models in agricultural object detection.

Contribution

The paper presents a novel active lighting-based camera system that ensures consistent image quality across lighting conditions, improving deep learning training efficiency in agriculture.

Findings

Images captured with active lighting are more consistent under different lighting conditions.

Deep neural networks trained on consistent data require four times less data.

Field experiments confirm improved detection accuracy with the proposed system.

Abstract

Object detection and semantic segmentation are two of the most widely adopted deep learning algorithms in agricultural applications. One of the major sources of variability in image quality acquired in the outdoors for such tasks is changing lighting condition that can alter the appearance of the objects or the contents of the entire image. While transfer learning and data augmentation to some extent reduce the need for large amount of data to train deep neural networks, the large variety of cultivars and the lack of shared datasets in agriculture makes wide-scale field deployments difficult. In this paper, we present a high throughput robust active lighting-based camera system that generates consistent images in all lighting conditions. We detail experiments that show the consistency in images quality leading to relatively fewer images to train deep neural networks for the task of object detection. We further present results from field experiment under extreme lighting conditions where images without active lighting significantly lack to provide consistent results. The experimental results show that on average, deep nets for object detection trained on consistent data required nearly four times less data to achieve similar level of accuracy. This proposed work could potentially provide pragmatic solutions to computer vision needs in agriculture.