Exploration of Optimized Semantic Segmentation Architectures for edge-Deployment on Drones
This work addresses efficient real-time image processing for drones, but it is incremental as it focuses on parameter tuning and optimization of existing methods.
The paper tackled optimizing semantic segmentation architectures for drone deployment by analyzing network parameters on the DroneDeploy benchmark, identifying FPN-EfficientNetB3 as optimal with an IoU score of 0.65 and F1-score of 0.71.
In this paper, we present an analysis on the impact of network parameters for semantic segmentation architectures in context of UAV data processing. We present the analysis on the DroneDeploy Segmentation benchmark. Based on the comparative analysis we identify the optimal network architecture to be FPN-EfficientNetB3 with pretrained encoder backbones based on Imagenet Dataset. The network achieves IoU score of 0.65 and F1-score of 0.71 over the validation dataset. We also compare the various architectures in terms of their memory footprint and inference latency with further exploration of the impact of TensorRT based optimizations. We achieve memory savings of ~4.1x and latency improvement of 10% compared to Model: FPN and Backbone: InceptionResnetV2.