Vessel segmentation is critical for disease diagnosis and surgical planning. Recently, the vessel segmentation method based on deep learning has achieved outstanding performance. However, vessel segmentation remains challenging due to thin vessels with low contrast that easily lose spatial information in the traditional U-shaped segmentation network. To alleviate this problem, we propose a novel and straightforward full-resolution network (FR-UNet) that expands horizontally and vertically through a multiresolution convolution interactive mechanism while retaining full image resolution. In FR-UNet, the feature aggregation module integrates multiscale feature maps from adjacent stages to supplement high-level contextual information. The modified residual blocks continuously learn multiresolution representations to obtain a pixel-level accuracy prediction map. Moreover, we propose the dual-threshold iterative algorithm (DTI) to extract weak vessel pixels for improving vessel connectivity. The proposed method was evaluated on retinal vessel datasets (DRIVE, CHASE_DB1, and STARE) and coronary angiography datasets (DCA1 and CHUAC). The results demonstrate that FR-UNet outperforms state-of-the-art methods by achieving the highest Sen, AUC, F1, and IOU on most of the above-mentioned datasets with fewer parameters, and that DTI enhances vessel connectivity while greatly improving sensitivity. The code is available at: https://github.com/lseventeen/FR-UNet .

Multispectral pedestrian detection, which consists of a color stream and thermal stream, is essential under conditions of insufficient illumination because the fusion of the two streams can provide complementary information for detecting pedestrians based on deep convolutional neural networks (CNNs). In this paper, we introduced and adapted a simple and efficient one-stage YOLOv4 to replace the current state-of-the-art two-stage fast-RCNN for multispectral pedestrian detection and to directly predict bounding boxes with confidence scores. To further improve the detection performance, we analyzed the existing multispectral fusion methods and proposed a novel multispectral channel feature fusion (MCFF) module for integrating the features from the color and thermal streams according to the illumination conditions. Moreover, several fusion architectures, such as Early Fusion, Halfway Fusion, Late Fusion, and Direct Fusion, were carefully designed based on the MCFF to transfer the feature information from the bottom to the top at different stages. Finally, the experimental results on the KAIST and Utokyo pedestrian benchmarks showed that Halfway Fusion was used to obtain the best performance of all architectures and the MCFF could adapt fused features in the two modalities. The log-average miss rate (MR) for the two modalities with reasonable settings were 4.91% and 23.14%, respectively.

An automatic region proposal network (ARPN) is proposed to generate bounding boxes with confidence scores for far-infrared (FIR) pedestrian detection. The model consists of two parts: first, the bounding boxes are predicted by the L2 loss function and a module is designed based on a convolutional neural network. This module is simple and only has two layers, each with a 1W1 kernel. Second, a score map is obtained through FIR pedestrian segmentation based on a feature pyramid network. The scores are taken as the confidence levels for the predicted bounding boxes. To obtain the scores, a new labelling method is also introduced in this paper for FIR image segmentation. We can obtain the bounding boxes per pixel directly and efficiently without any manually designed hyper parameters related to the anchor boxes. To validate the model, this paper uses the LSI, CVC09, CVC14 and SCUT FIR pedestrian detection datasets in the experiments. The datasets consist of different sizes of FIR images collected from several different cameras. The datasets contain different outdoor urban scenes collected at different times, from day to night. The recall vs number of proposals, average recall and recall at IoU 0.5 are used to evaluate the proposed method and log-average miss rate is used to evaluate final detection results. Compared with other algorithms, experiments on most of the data sets also show better performance.

Pedestrian detection based on visual sensors has made significant progress, in which region proposal is the key step. There are two mainstream methods to generate region proposals: anchor‐based and anchor‐free. However, anchor‐based methods need more hyperparameters related to anchors for training compared with anchor‐free methods. In this paper, we propose a novel multiscale anchor‐free (MSAF) region proposal network to obtain proposals, especially for small‐scale pedestrians. It usually has several branches to predict proposals and assigns ground truth according to the height of pedestrian. Each branch consists of two components: one is feature extraction, and the other is detection head. Adapted channel feature fusion (ACFF) is proposed to select features at different levels of the backbone to effectively extract features. The detection head is used to predict the pedestrian center location, center offsets, and height to get bounding boxes. With our classifier, the detection performance can be further improved, especially for small‐scale pedestrians. The experiments on the Caltech and CityPersons demonstrate that the MSAF can significantly boost the pedestrian detection performance and the log‐average miss rate (MR) on the reasonable setting is 3.97% and 9.5%, respectively. If proposals are reclassified with our classifier, MR is 3.38% and 8.4%. The detection performance can be further improved, especially for small‐scale pedestrians.