Adaptive multilevel attention deeplabv3+ with heuristic based frame work for semantic segmentation of aerial images using improved golden jackal optimization algorithm

Semantic segmentation of small-scale objects in aerial images is challenging due to low-level characteristics in neural networks and varying information in feature maps. Deeplab models struggle with poor edge refinement, resulting in rough borders, and fail to fully exploit relationships between pixel categories at different distances. To addressing the issue in deeplab series, an adaptive multi-level attention based deeplabv3+ (AMLA-Deeplabv3+) with improved golden jackal optimization algorithm is implemented in this paper. Multi-level attention unit has been included in the Atrous spatial pyramid pooling module in the encoder section of deeplabv3+ to bridge the semantic feature gap among encoders output. To put more weights on relevant features squeeze and excitation units has been included in the decoder section of deeplabv3+. The improved golden jackal optimization (IGJO) algorithm is deployed to fine tune the hyper parameters such as number of hidden neurons, epochs, learning rate and batch size of deeplabv3+. The proposed AMLA-Deeplabv3+ is tested on two publicly available datasets named semantic segmentation of aerial imagery and aerial image segmentation. The proposed model achieves better segmentation outcomes in terms of accuracy of 99.65 %, Precision of 97.21 %, F1-score of 99.48 % and mean intersection over union of 98.44 % with a computation time of 3.0231 min. The experimental outcomes shows that the proposed model's efficiency is superior to other conventional techniques. • To design a deep learning framework named Adaptive multi-level attention based deeplabv3+ (AMLA-Deeplabv3+) using Improved Golden Jackal Optimization (IGJO) algorithm for semantic segmentation of aerial images. • To develop a new optimization scheme called the improved golden jackal optimization algorithm for optimizing the hyper parameters like number of hidden neurons, epochs, learning rate and batch size of the multilevel attention based deeplabV3+ model. • To improve the overall segmentation accuracy and minimize the computational complexity by tuning the hyper parameters of multilevel attention based DeepLabV3+ model like number of hidden neurons, epochs, learning rate and batch size. • To validate and compare the working of the proposed semantic segmentation model with other conventional segmentation approaches and with traditional heuristic approaches to prove the enhanced efficacy. • The paper may gain high interest from the readers and experts of. ✓ Semantic Segmentation ✓ Aerial Images ✓ Deep Learning ✓ Heuristic algorithm