Machine Vision for Smart Trap Bandwidth Optimization and New Threat Identification

Abstract

With the rising impact of climate change on agriculture, insect-borne diseases are proliferating. There is a need to monitor the appearance of new vectors to take preventive actions that allow us to reduce the use of chemical pesticides and treatment costs. Thus, agriculture requires advanced monitoring tools for early pest and disease detection. This work presents a new concept design for a scalable, interoperable and cost-effective smart trap that can digitize daily images of crop-damaging insects and send them to the cloud server. However, this procedure can consume approximately twenty megabytes of data per day, which can increase the network infrastructure costs and requires a large bandwidth. Thus, a two-stage system is also proposed to locally detect and count insects. In the first stage, a lightweight approach based on the SVM model and a visual descriptor is used to classify and detect all regions of interest (ROIs) in the images that contain the insects. Instead of the full image, only the ROIs are then sent to a second stage in the pest monitoring system, where they will be classified. This approach can reduce, by almost 99%, the amount of data sent to the cloud server. Additionally, the classifier will identify unclassified insects in each ROI, which can be sent to the cloud for further training. This approach reduces the internet bandwidth usage and helps to identify unclassified insects and new threats. In addition, the classifier can be trained with supervised data on the cloud and then sent to each smart trap. The proposed approach is a promising new method for early pest and disease detection.

Keywords

• bandwidth optimization
• SVM
• pest detection
• smart trap