Flying Bird Object Detection Algorithm in Surveillance Video Based on Motion Information

A flying bird object detection algorithm based on motion information (FBOD-BMI) is proposed to solve the problem that the features of the object are not obvious in a single frame, and the size of the object is small [low signal-to-noise ratio (SNR)] in surveillance video. First, a ConvLSTM-PAN model structure is designed to capture suspicious flying bird objects, in which the convolutional long and short time memory (ConvLSTM) network aggregates the spatio-temporal features of the flying bird object in adjacent multiframe before the input of the general model [path aggregation network (PAN)], and the PAN model locates the suspicious flying bird objects. Then, an object tracking algorithm is used to track suspicious flying bird objects and calculate their motion range (MR). At the same time, the size of the MR of the suspicious flying bird object is adjusted adaptively according to its speed of movement (specifically, if the bird moves slowly, its MR will be expanded according to the speed of the bird to ensure the environmental information needed to detect the flying bird object). Adaptive spatio-temporal cubes (ASt-Cubes) of the flying bird objects are generated to ensure that the SNR of the flying bird objects is improved, and the necessary environmental information is retained adaptively. Finally, a lightweight U-shape net (LW-USN) based on ASt-Cubes is designed to detect flying bird objects, which rejects the false detections of the suspicious flying bird objects and returns the position of the real flying bird objects. The monitoring video including the flying birds is collected in the unattended traction substation as the experimental dataset to verify the performance of the algorithm. The experimental results show that the flying bird object detection method based on motion information proposed in this article can effectively detect the flying bird object in surveillance video.