Fuzzy wavelet neural network driven vehicle detection on remote sensing imagery

Remote sensing-based target detection process is applied to spot the targeted objects in remote sensing images (RSIs). However, it is challenging to detect small-sized vehicles in RSIs. The current study designs a Chicken Swarm Optimization with Transfer Learning-Driven Vehicle Detection and Classification on Remote Sensing Imagery (CSOTL-VDCRS) technique to resolve these issues. The presented CSOTL-VDCRS technique employs the mask-region based Convolutional Neural Network (Mask RCNN) technique for the detection of the vehicles. Once the vehicles in the RSIs are detected, the next step is to classify them using the Fuzzy Wavelet Neural Network (FWNN) model. To enhance the performance of the proposed model in terms of vehicle detection, the CSO technique is used as a hyperparameter optimizer for the Mask RCNN technique. The proposed CSOTL-VDCRS technique was experimentally validated using the benchmark dataset, and the outcomes demonstrate its superior performance over other existing models.