Alert button
Picture for İbrahim Batuhan Akkaya

İbrahim Batuhan Akkaya

Alert button

Focus-and-Detect: A Small Object Detection Framework for Aerial Images

Mar 24, 2022
Onur Can Koyun, Reyhan Kevser Keser, İbrahim Batuhan Akkaya, Behçet Uğur Töreyin

Figure 1 for Focus-and-Detect: A Small Object Detection Framework for Aerial Images
Figure 2 for Focus-and-Detect: A Small Object Detection Framework for Aerial Images
Figure 3 for Focus-and-Detect: A Small Object Detection Framework for Aerial Images
Figure 4 for Focus-and-Detect: A Small Object Detection Framework for Aerial Images

Despite recent advances, object detection in aerial images is still a challenging task. Specific problems in aerial images makes the detection problem harder, such as small objects, densely packed objects, objects in different sizes and with different orientations. To address small object detection problem, we propose a two-stage object detection framework called "Focus-and-Detect". The first stage which consists of an object detector network supervised by a Gaussian Mixture Model, generates clusters of objects constituting the focused regions. The second stage, which is also an object detector network, predicts objects within the focal regions. Incomplete Box Suppression (IBS) method is also proposed to overcome the truncation effect of region search approach. Results indicate that the proposed two-stage framework achieves an AP score of 42.06 on VisDrone validation dataset, surpassing all other state-of-the-art small object detection methods reported in the literature, to the best of authors' knowledge.

* Signal Processing: Image Communication, Volume 104, May 2022, 116675  
* 12 pages, 6 figures 
Viaarxiv icon