Object detection remains an important and ever-present component of computer vision applications. We demonstrate that our method shows a better performance than some previous works.
It contains about 15,000 images for training and about 6,000 images for testing with ground truth annotations for moving objects. We present the experimental results on our dataset. Finally, we process a threshold processing to distinguish between object pixels and non-object pixels. Our network takes the past five frames registered with respect to the last frame and produces a heatmap prediction for moving objects. These sublayers play a role in detecting objects with different sizes or speeds, which is very important because objects that are closer to the camera look bigger and faster in oblique images. Our network has a CNN (Convolutional Neural Network) architecture with the first and second layer containing sublayers with different kernel sizes. In this paper, we propose a deep learning based moving object detection method for oblique images without using future frames. Also, many methods use future frames to detect moving objects in the current frame, which causes delayed detection. However, most of the works did not take account of the characteristics of oblique images. Moving object detection from UAV/aerial images is one of the essential tasks in surveillance systems.