Swarm Intelligence with Deep Transfer Learning Driven Aerial Image Classification Model on UAV Networks

Nowadays, unmanned aerial vehicles (UAVs) have gradually attracted the attention of many academicians and researchers. The UAV has been found to be useful in variety applications, such as disaster management, intelligent transportation system, wildlife monitoring, surveillance. In images, learning effectual image representation was central scene classifier method. previous approach classification method depends on feature coding models with lower-level handcrafted features or unsupervised learning. emergence convolutional neural network (CNN) is developing techniques more effectively. Due limited resource UAVs, it can difficult fine-tune hyperparameter trade-offs amongst computation complexity results. This article focuses design swarm intelligence deep transfer driven (SIDTLD-AIC) model networks. presented SIDTLD-AIC involves proper identification images into distinct kinds. For accomplishing this, follows a extraction module using RetinaNet which optimization process performed by use salp algorithm (SSA). addition, cascaded long short term memory (CLSTM) executed for classifying images. At last, seeker (SOA) applied optimizer CLSTM thereby results enhanced accuracy. To assure better performance model, wide range simulations are implemented outcomes investigated aspects. comparative study reported over recent approaches.