A Dual-Channel and Frequency-Aware Approach for Lightweight Video Instance Segmentation
Open Access
Abstract
Video instance segmentation, a key technology for intelligent sensing in visual perception, plays a key role in automated surveillance, robotics, and smart cities. These scenarios rely on real-time and efficient target-tracking capabilities for accurate perception and intelligent analysis of dynamic environments. However, traditional video instance segmentation methods face complex models, high computational overheads, and slow segmentation speeds in time-series feature extraction, especially in resource-constrained environments. To address these challenges, a Dual-Channel and Frequency-Aware Approach for Lightweight Video Instance Segmentation (DCFA-LVIS) is proposed in this paper. In feature extraction, a DCEResNet backbone network structure based on a dual-channel feature enhancement mechanism is designed to improve the model’s accuracy by enhancing the feature extraction and representation capabilities. In instance tracking, a dual-frequency perceptual enhancement network structure is constructed, which uses an independent instance query mechanism to capture temporal information and combines with a frequency-aware attention mechanism to capture instance features on different attention layers of high and low frequencies, respectively, to effectively reduce the complexity of the model, decrease the number of parameters, and improve the segmentation efficiency. Experiments show that the model proposed in this paper achieves state-of-the-art segmentation performance with few parameters on the YouTube-VIS dataset, demonstrating its efficiency and practicality. This method significantly enhances the application efficiency and adaptability of visual perception intelligent sensing technology in video data acquisition and processing, providing strong support for its widespread deployment.Keywords
Funding Information
- Key Research and Development Plan Project of Heilongjiang (JD2023SJ19, YQ2022F014)
- Heilongjiang Provincial Natural Science Foundation of China (JD2023SJ19, YQ2022F014)
This publication has 39 references indexed in Scilit:
- SeqFormer: Sequential Transformer for Video Instance Segmentation2022
- In Defense of Online Models for Video Instance Segmentation2022
- Occluded Video Instance Segmentation: A BenchmarkInternational Journal of Computer Vision, 2022
- PointRend Segmentation for a Densely Occluded Moving Object in a Video2021
- STEm-Seg: Spatio-Temporal Embeddings for Instance Segmentation in Videos2020
- SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation2020
- End-to-End Object Detection with Transformers2020
- V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation2016
- Microsoft COCO: Common Objects in Context2014
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955