Using Convolutional Neural Networks to Count Palm Trees in Satellite Images

In this paper we propose a supervised learning system for counting and localizing palm trees in high-resolution, panchromatic satellite imagery (40cm/pixel to 1.5m/pixel). A convolutional neural network classifier trained on a set of palm and no-palm images is applied across a satellite image scene in a sliding window fashion. The resultant confidence map is smoothed with a uniform filter. A non-maximal suppression is applied onto the smoothed confidence map to obtain peaks. Trained with a small dataset of 500 images of size 40x40 cropped from satellite images, the system manages to achieve a tree count accuracy of over 99%.

[1]  Tao Wang,et al.  End-to-end text recognition with convolutional neural networks , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[2]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[3]  Naif Alajlan,et al.  Efficient Framework for Palm Tree Detection in UAV Images , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[4]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[5]  Preesan Rakwatin,et al.  Oil Palm Tree Detection with High Resolution Multi-Spectral Satellite Imagery , 2014, Remote. Sens..

[6]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.