In the practical application scenarios of safety helmet detection, the lightweight algorithm You Only Look Once (YOLO) v3-tiny is easy to be deployed in embedded devices because its number of parameters is small. However, its detection accuracy is relatively low, which is why it is not suitable for detecting multi-scale safety helmets. The safety helmet detection algorithm (named SAS-YOLOv3-tiny) is proposed in this paper to balance detection accuracy and model complexity. A light Sandglass-Residual (SR) module based on depthwise separable convolution and channel attention mechanism is constructed to replace the original convolution layer, and the convolution layer of stride two is used to replace the max-pooling layer for obtaining more informative features and promoting detection performance while reducing the number of parameters and computation. Instead of two-scale feature prediction, three-scale feature prediction is used here to improve the detection effect about small objects further. In addition, an improved spatial pyramid pooling (SPP) module is added to the feature extraction network to extract local and global features with rich semantic information. Complete-Intersection over Union (CIoU) loss is also introduced in this paper to improve the loss function for promoting positioning accuracy. The results on the self-built helmet dataset show that the improved algorithm is superior to the original algorithm. Compared with the original YOLOv3-tiny, the SAS-YOLOv3-tiny has significantly improved all metrics (including Precision (P), Recall (R), Mean Average Precision (mAP), F1) at the expense of only a minor speed while keeping fewer parameters and amounts of calculation. Meanwhile, the SAS-YOLOv3-tiny algorithm shows advantages in accuracy compared with lightweight object detection algorithms, and its speed is faster than the heavyweight model.

In terms of small objects in traffic scenes, general object detection algorithms have low detection accuracy, high model complexity, and slow detection speed. To solve the above problems, an improved algorithm (named YOLO-MXANet) is proposed in this paper. Complete-Intersection over Union (CIoU) is utilized to improve loss function for promoting the positioning accuracy of the small object. In order to reduce the complexity of the model, we present a lightweight yet powerful backbone network (named SA-MobileNeXt) that incorporates channel and spatial attention. Our approach can extract expressive features more effectively by applying the Shuffle Channel and Spatial Attention (SCSA) module into the SandGlass Block (SGBlock) module while increasing the parameters by a small number. In addition, the data enhancement method combining Mosaic and Mixup is employed to improve the robustness of the training model. The Multi-scale Feature Enhancement Fusion (MFEF) network is proposed to fuse the extracted features better. In addition, the SiLU activation function is utilized to optimize the Convolution-Batchnorm-Leaky ReLU (CBL) module and the SGBlock module to accelerate the convergence of the model. The ablation experiments on the KITTI dataset show that each improved method is effective. The improved algorithm reduces the complexity and detection speed of the model while improving the object detection accuracy. The comparative experiments on the KITTY dataset and CCTSDB dataset with other algorithms show that our algorithm also has certain advantages.

Visual Transformers (ViTs) have shown impressive performance due to their powerful coding ability to catch spatial and channel information. MetaFormer gives us a general architecture of transformers consisting of a token mixer and a channel mixer through which we can generally understand how transformers work. It is proved that the general architecture of the ViTs is more essential to the models’ performance than self-attention mechanism. Then, Depth-wise Convolution layer (DwConv) is widely accepted to replace local self-attention in transformers. In this work, a pure convolutional "transformer" is designed. We rethink the difference between the operation of self-attention and DwConv. It is found that the self-attention layer, with an embedding layer, unavoidably affects channel information, while DwConv only mixes the token information per channel. To address the differences between DwConv and self-attention, we implement DwConv with an embedding layer before as the token mixer to instantiate a MetaFormer block and a model named EmbedFormer is introduced. Meanwhile, SEBlock is applied in the channel mixer part to improve performance. On the ImageNet-1K classification task, EmbedFormer achieves top-1 accuracy of 81.7% without additional training images, surpassing the Swin transformer by +0.4% in similar complexity. In addition, EmbedFormer is evaluated in downstream tasks and the results are entirely above those of PoolFormer, ResNet and DeiT. Compared with PoolFormer-S24, another instance of MetaFormer, our EmbedFormer improves the score by +3.0% box AP/+2.3% mask AP on the COCO dataset and +1.3% mIoU on the ADE20K.

Although wrist-type photoplethysmographic (hereafter referred to as WPPG) sensor signals can measure heart rate quite conveniently, the subjects’ hand movements can cause strong motion artifacts, and then the motion artifacts will heavily contaminate WPPG signals. Hence, it is challenging for us to accurately estimate heart rate from WPPG signals during intense physical activities. The WWPG method has attracted more attention thanks to the popularity of wrist-worn wearable devices. In this paper, a mixed approach called Mix-SVM is proposed, it can use multi-channel WPPG sensor signals and simultaneous acceleration signals to measurement heart rate. Firstly, we combine the principle component analysis and adaptive filter to remove a part of the motion artifacts. Due to the strong relativity between motion artifacts and acceleration signals, the further denoising problem is regarded as a sparse signals reconstruction problem. Then, we use a spectrum subtraction method to eliminate motion artifacts effectively. Finally, the spectral peak corresponding to heart rate is sought by an SVM-based spectral analysis method. Through the public PPG database in the 2015 IEEE Signal Processing Cup, we acquire the experimental results, i.e., the average absolute error was 1.01 beat per minute, and the Pearson correlation was 0.9972. These results also confirm that the proposed Mix-SVM approach has potential for multi-channel WPPG-based heart rate estimation in the presence of intense physical exercise.

Small object detection has long been one of the most formidable challenges in computer vision due to the poor visual features and high noise of surroundings behind them. However, small targets in traffic scenes encompass a multitude of complex visual interfering factors, bearing crucial information such as traffic signs, traffic lights, and pedestrians. Given the inherent difficulties faced by generic models in addressing these issues, we conduct a comprehensive investigation on small target detection in this application scenario. In this work, we present a Cross-Layer Feature Fusion and Channel Attention algorithm based on a lightweight YOLOv5s design for traffic small target detection, named CFA-YOLO. To enhance the sensitivity of the model toward vital features, we embed the channel-guided Squeeze-and-Excitation (SE) block in the deep layer of the backbone. Moreover, the most excellent innovation of our work belongs to the effective cross-layer feature fusion method, which maintains robust feature fusion and information interaction capabilities; in addition, it simplifies redundant parameters compared with the baseline model. To align with the output features of the neck network, we adjusted the detection heads from three to two. Furthermore, we also applied the decoupled detection head for classification and bounding box regression tasks, respectively. This approach not only achieves real-time detection standards, but also improves the overall training results in parameter-friendly manner. The CFA-YOLO model significantly pays a lot of attention to the detail features of small targets, thereby it also has a great advantage in addressing the issue of poor performance in traffic small target detection results. Vast experiments have validated the efficiency and effectiveness of our proposed method in traffic small object detection. Compared with the latest lightweight detectors, such as YOLOv7-Tiny and YOLOv8s, our method consistently achieves superior performance both in terms of the model’s accuracy and complexity.

Aerial tracking is an essential component of vision-based measurement and UAV systems, playing a crucial role in autonomous navigation, intelligent transportation, and remote sensing. However, aerial scenarios present unique challenges such as rapid motion, scale variation, and camera movement. Most existing tracking methods either use CNNs for feature extraction or rely on Transformers for global feature modeling, but these approaches struggle to balance accuracy and real-time performance. To address this issue, this paper proposes MISATrack, an efficient Siamese network model that integrates frequency domain encoder and scale-frequency linear attention mechanism. Firstly, we apply discrete wavelet transform to convert the input image into the frequency domain, and then enhance its diverse visual information by our multi-frequency integration strategy. In addition, we further design scale-frequency linear attention module for hierarchical feature fusion. This scheme greatly facilitates representation learning with few computation overhead, resulting in more robust object tracking. The proposed tracker is evaluated using four UAV tracking benchmarks: DTB70, UAV123, UAV123@10fps and UAVTrack112. Experimental results indicate that MISATrack outperforms most state-of-the-art trackers while maintaining real-time tracking. The code is publicly available at https://github.com/Wang123z/MISATrack.