Dynamic-Aware Network for Moving Object Detection

Moving object detection (MOD) plays an important role in many applications that aim to identify regions of interest in videos. However, most existing MOD methods ignore the variability brought by time-varying information. Additionally, many network frameworks primarily focus on low-level feature learning, neglecting the higher-level contextual understanding required for accurate detection. To solve the above issues, we propose a symmetric Dynamic-Aware Network (DAN) for MOD. DAN explores the interactions between different types of information via structural design and feature optimization. To locate the object position quickly, we build a Siamese convolutional network to emphasize changes in the scene. Subsequently, a Change-Aware Module (CAM) is designed, which can maximize the perception of object change cues by exploiting complementary depth-varying features and different levels of disparity information, thereby enhancing the feature discrimination capability of the network. Moreover, to reinforce the effective transfer between features, we devise a Motion-Attentive Selection Module (MASM) to construct an autonomous decoder for augmenting detail representation. Experimental results on benchmark datasets indicate the rationality and validity of the proposed approach.