Vehicle trajectory is crucial for autonomous driving. Relatively scattered trajectory data points pose difficulties in modeling the motion’s inherent continuity in spatial and temporal dimensions. Additionally, identifying the driving patterns of vehicles from trajectories is also a significant challenge. These implicit characteristic patterns are difficult to discern from the complex details of the trajectory data. To address these issues, we propose a new framework called Wavelet-Mamba Trajectory Prediction (WMTP), which fuses wavelet analysis through state-space modeling to capture global trends in driving patterns and details of vehicle motion. The approach employs the Discrete Wavelet Transform (DWT) to decompose trajectory data into wavelet coefficients in different time scales and frequencies, and then utilizes these coefficients to generate the trajectory through the Inverse Discrete Wavelet Transform (IDWT). An encoder-decoder neural architecture is proposed for learning potential temporal features from the input trajectory sequences, and these features are projected into the wavelet domain. Wavelet coefficients of future trajectories are generated using different scale-oriented decoders. The estimated coefficients are further used to realize the trajectory prediction via the IDWT module. Experiments demonstrate that WMTP exhibits excellent performance on three large-scale real-world trajectory prediction datasets, with promising robustness and inference speed. The research findings also verify the effectiveness of time - frequency analysis in trajectory prediction tasks.

To improve the compression performance of screen content coding, extension coding standards (HEVC-SCC, VVC-SCC) have been developed. However, considering the compression ratio alone may lead to packet losses in bitstreams which may cause plenty of images decoded incorrectly, degrading the video quality at the receiver side. Thus, it urgently needs to study source-channel jointly coding scheme of screen content video. The most significant challenge lies in the complex spatial-temporal characteristics of screen content video, which complicate the creation of an accurate end-to-end distortion model. In this article, we delve into the traits of screen content video and construct an end-to-end distortion model. Building upon this, we introduce an error resilient coding scheme specifically for screen content video. More specifically, we first consider the characteristic of non-stationary temporal domain variation and classify the screen content images into three types of frames using a fast block-searching method. We then propose an adaptive error concealment method, taking into account the spatial-temporal prediction characteristics. Following this, we derive a pixel-level end-to-end distortion model and incorporate it into the rate distortion optimization process. Our experimental results reveal that, compared to state-of-the-art methods, our proposed method significantly enhances both objective and subjective quality across a variety of channel conditions.