The presence of chironomid larvae in tap water has sparked public concern regarding the water supply system in South Korea. Despite ongoing efforts to establish a safe water supply system, entirely preventing larval occurrences remains a significant challenge. Therefore, we developed a real-time chironomid larva detection system (RT-CLAD) based on deep learning technology, which was implemented in drinking water treatment plants. The acquisition of larval images was facilitated by a multi-spectral camera with a wide spectral range, enabling the capture of unique wavelet bands associated with larvae. Three state-of-the-art deep learning algorithms, namely the convolutional neural network (CNN), you only look once (YOLO), and residual neural network (ResNet), renowned for their exceptional performance in object detection tasks, were employed. Following a comparative analysis of these algorithms, the most accurate and rapid model was selected for RT-CLAD. To achieve the efficient and accurate detection of larvae, the original images were transformed into a specific wavelet format, followed by preprocessing to minimize data size. Consequently, the CNN, YOLO, and ResNet algorithms successfully detected larvae with 100% accuracy. In comparison to YOLO and ResNet, the CNN algorithm demonstrated greater efficiency because of its faster processing and simpler architecture. We anticipate that our RT-CLAD will address larva detection challenges in water treatment plants, thereby enhancing water supply security.
Keywords: chironomid larvae; deep learning; drinking water treatment plant; larval detection system; multi-spectral image.