Recently, deep convolutional neural networks (DCNN) have been widely used in semantic segmentation tasks and have achieved high segmentation accuracy. However, most algorithms based on DCNN have high computational complexity, making them unsuitable for real‐time segmentation. To solve this problem, this paper proposes a real‐time semantic segmentation algorithm based on the STDC network. The algorithm adopts an “encoder–decoder” embedded in a U‐shaped architecture to realize real‐time segmentation while maintaining high accuracy. Following the encoder, a mixed pooling attention module is designed to expand the receptive field, enhancing the network model’s learning ability in complex scenarios. Then, a feature fusion module is used for combining features from different stages, and channel attention based on atrous convolution is employed to expand the receptive field and avoid dimensionality reduction learning. Finally, a Tversky‐based detail loss function is used to encode more spatial details. The proposed algorithm was extensively tested on the challenging Cityscapes and CamVid datasets, and the experimental results showed that the proposed algorithm obtained 76.4% and 72.8% of mIoU, respectively. Meanwhile, our algorithm achieves 105.2 FPS and 165.6 FPS inference speed with a single NVIDIA GTX 1080Ti GPU, meeting the real‐time segmentation requirements. The proposed algorithm can conduct real‐time segmentation while maintaining high accuracy, achieving a good balance between accuracy and speed.

Discriminative correlation filters (DCFs) have shown promising tracking performance in recent years thanks to the powerful representation ability of deep features. However, a large number of target-irrelevant channels in deep features limits the tracking performance and increases the computational cost. To eliminate the negative impact of noisy channels and improve the utilization efficiency of deep features in DCF-based trackers, we present an adaptive feature channel selection method for robust visual tracking. Our method adaptively chooses the most discriminative channels to learn a more robust target appearance model, which is achieved by evaluating the energy relationship between background and foreground in each feature channel. Moreover, according to the feedback of channel selection, an adaptive model update strategy is proposed to alleviate the model degradation problem caused by incorrect model updating. Extensive experimental results obtained on five popular tracking benchmarks demonstrate the effectiveness of the proposed algorithm and its superiority over the state-of-the-art trackers.