Object Counting for Remote-Sensing Images via Adaptive Density Map-Assisted Learning

Object counting has attracted a lot of attention in remote-sensing image analysis. In density map-based object counting algorithms, the ground-truth density maps generated by fix-sized Gaussian kernels ignore the spatial features of the objects. In this article, an adaptive density map-assisted learning (ADMAL) algorithm is proposed, which taps into spatial features of the objects from the beginning phase of ground-truth density map generation (DMG). ADMAL consists of two networks: a contexture-aware DMG (CADMG) network and a transformer-based density map estimation (TDME) network. The CADMG network is designed to generate a ground-truth density map from each annotated point map. Compared with Gaussian convolved density maps, the ground-truth density maps generated by CADMG will be tailored according to the texture and neighborhood relationship among objects, which can promote the learning effect of the TDME network. TDME is the core network for object counting. The backbone of the TDME network adopts a Swin transformer structure, the self-attention mechanism of which possesses a larger receptive field for effective feature extraction in remote-sensing images. Comprehensive experiments prove that the ground-truth density map generated by CADMG can help various density map estimation (DME) networks achieve better training effects, among which TDME achieves the best performances. Moreover, the ADMAL algorithm can achieve preferable object counting performances for both satellite-based and drone-based images. Code and pretrained models are available at
https://github.com/gcding/ADMAL-pytorch
.