TL;DR
This paper introduces Sim2Air, a synthetic aerial dataset generated with shape-focused object representation and texture randomization, improving UAV monitoring detection performance under challenging conditions.
Contribution
It presents a novel synthetic dataset creation method emphasizing shape over texture, enhancing UAV detection models' robustness in difficult lighting and small object scenarios.
Findings
Increased mAP for YOLO and Faster R-CNN on real UAV datasets.
Texture randomization improves detection under challenging illumination.
Shape-based representation enhances generalization across domains.
Abstract
In this paper we propose a novel approach to generate a synthetic aerial dataset for application in UAV monitoring. We propose to accentuate shape-based object representation by applying texture randomization. A diverse dataset with photorealism in all parameters such as shape, pose, lighting, scale, viewpoint, etc. except for atypical textures is created in a 3D modelling software Blender. Our approach specifically targets two conditions in aerial images where texture of objects is difficult to detect, namely challenging illumination and objects occupying only a small portion of the image. Experimental evaluation of YOLO and Faster R-CNN detectors trained on synthetic data with randomized textures confirmed our approach by increasing the mAP value (17 and 3.7 percentage points for YOLO; 20 and 1.1 percentage points for Faster R-CNN) on two test datasets of real images, both containing…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsTest · You Only Look Once · Convolution · Region Proposal Network · Faster R-CNN · RoIAlign · RoIPool · Softmax
