Ground mobile target detection based on bottom-up and top-down saliency combination

We proposed a saliency based algorithm to detect the ground mobile targets, such as plane and vehicle, in the images. The algorithm combines the bottom-up and top-down mode to detect the targets. Firstly, in the bottom-up mode, the algorithm extracts the low level image features, such as intensity, standard deviation and Gabor features, to calculate the difference between the current pixel and the pixel around it and use the difference as the bottom-up saliency of the pixel; Then, the algorithm extracts the HOG features of the plane and vehicle targets to train a SVM classifier, which can learn the high level knowledge of the target. When testing on a new image, the classifier uses the knowledge to predict the possibility of appearance of the target as the top-down saliency of each position of the image; Finally, we combine the two saliency maps to get the final saliency map and use it to detect targets in the image. Experiments show that the algorithm can effectively detect the ground mobile targets robustly in complex backgrounds.