YOLO-FR: A YOLOv5 Infrared Small Target Detection Algorithm Based on Feature Reassembly Sampling Method.

The loss of infrared dim-small target features in the network sampling process is a major factor affecting its detection accuracy. In order to reduce this loss, this paper proposes YOLO-FR, a YOLOv5 infrared dim-small target detection model, based on feature reassembly sampling, which refers to scaling the feature map size without increasing or decreasing the current amount of feature information. In this algorithm, an STD Block is designed to reduce the loss of features during down-sampling by saving spatial information to the channel dimension, and the CARAFE operator, which increases the feature map size without changing the feature mapping mean, is adopted to ensure that features are not distorted by relational scaling. In addition, in order to make full use of the detailed features extracted by the backbone network, the neck network is improved in this study so that the feature extracted after one down-sampling of the backbone network is fused with the top-level semantic information by the neck network to obtain the target detection head with a small receptive field. The experimental results show that the YOLO-FR model proposed in this paper achieved 97.4% on mAP50, which is a 7.4% improvement compared to the original network, and it also outperformed J-MSF and YOLO-SASE.

Visible-Image-Assisted Nonuniformity Correction of Infrared Images Using the GAN with SEBlock.

Aiming at reducing image detail loss and edge blur in the existing nonuniformity correction (NUC) methods, a new visible-image-assisted NUC algorithm based on a dual-discriminator generative adversarial network (GAN) with SEBlock (VIA-NUC) is proposed. The algorithm uses the visible image as a reference for better uniformity. The generative model downsamples the infrared and visible images separately for multiscale feature extraction. Then, image reconstruction is achieved by decoding the infrared feature maps with the assistance of the visible features at the same scale. During decoding, SEBlock, a channel attention mechanism, and skip connection are used to ensure that more distinctive channel and spatial features are extracted from the visible features. Two discriminators based on vision transformer (Vit) and discrete wavelet transform (DWT) were designed, which perform global and local judgments on the generated image from the texture features and frequency domain features of the model, respectively. The results are then fed back to the generator for adversarial learning. This approach can effectively remove nonuniform noise while preserving the texture. The performance of the proposed method was validated using public datasets. The average structural similarity (SSIM) and average peak signal-to-noise ratio (PSNR) of the corrected images exceeded 0.97 and 37.11 dB, respectively. The experimental results show that the proposed method improves the metric evaluation by more than 3%.

A Design of Electromagnetic Velocity Sensor with High Sensitivity Based on Dual-Magnet Structure.

The most permanent magnets in current electromagnetic velocity sensors are magnet cylinders that have been axially magnetized, with magnetic boots changing the propagation direction of the magnetic induction lines of the magnet cylinders. However, the magnetic field generated by the magnet cylinders is not fully utilized, which leads to uneven magnetic field intensity of the working air-gap and high magnetic field intensity of the nonworking air-gap. We propose a novel dual-magnet structure (DM) mainly consisting of two magnet loops that are magnetized radially and a magnetic conductive shaft, adopting a concentric nested configuration. The dual-magnet structure can make the magnetic induction lines enter the working air-gap directly from the magnet and increase the effective magnetic field, which is perpendicular to the coils in the working air-gap. This design can further improve the sensitivity of a velocity sensor and enhance its ability to detect weak signals in microtremor exploration. The validity of the dual-magnet structure has been established by numerical simulations and verified by experiments. The results reveal that the magnetic field intensity is increased by 29.18% and the sensitivity is improved by 23.9%, when the total volume and material of the magnet are unchanged. The full utilization of the material is achieved without increasing the complexity of the structure.

YOLO-SASE: An Improved YOLO Algorithm for the Small Targets Detection in Complex Backgrounds.

To improve the detection ability of infrared small targets in complex backgrounds, an improved detection algorithm YOLO-SASE is proposed in this paper. The algorithm is based on the YOLO detection framework and SRGAN network, taking super-resolution reconstructed images as input, combined with the SASE module, SPP module, and multi-level receptive field structure while adjusting the number of detection output layers through exploring feature weight to improve feature utilization efficiency. Compared with the original model, the accuracy and recall rate of the algorithm proposed in this paper were improved by 2% and 3%, respectively, in the experiment, and the stability of the results was significantly improved in the training process.

Multirobot Collaborative Pursuit Target Robot by Improved MADDPG.

Policy formulation is one of the main problems in multirobot systems, especially in multirobot pursuit-evasion scenarios, where both sparse rewards and random environment changes bring great difficulties to find better strategy. Existing multirobot decision-making methods mostly use environmental rewards to promote robots to complete the target task that cannot achieve good results. This paper proposes a multirobot pursuit method based on improved multiagent deep deterministic policy gradient (MADDPG), which solves the problem of sparse rewards in multirobot pursuit-evasion scenarios by combining the intrinsic reward and the external environment. The state similarity module based on the threshold constraint is as a part of the intrinsic reward signal output by the intrinsic curiosity module, which is used to balance overexploration and insufficient exploration, so that the agent can use the intrinsic reward more effectively to learn better strategies. The simulation experiment results show that the proposed method can improve the reward value of robots and the success rate of the pursuit task significantly. The intuitive change is obviously reflected in the real-time distance between the pursuer and the escapee, the pursuer using the improved algorithm for training can get closer to the escapee more quickly, and the average following distance also decreases.

High Precision Visual Dimension Measurement Method with Large Range Based on Multi-Prism and M-Array Coding.

The visual dimension measurement method based on non-splicing single lens has the contradiction between accuracy and range of measurement, which cannot be considered simultaneously. In this paper, a multi-camera cooperative measurement method without mechanical motion is proposed for the dimension measurement of thin slice workpiece. After the calibration of the multi-camera imaging system is achieved through a simple and efficient scheme, the high-precision dimension measurement with a large field of view can be completed through a single exposure. First, the images of the edges of the workpiece are compressed and combined by splitting and merging light through the multi-prism system, and the results are distributed to multiple cameras by changing the light path. Then, the mapping relationship between the global measurement coordinates and the image coordinates of each camera is established based on the globally unique M-array coding, and the image distortion is corrected by the coding unit composed of black and white blocks. Finally, the edge is located accurately by edge point detection at the sub-pixel level and curve fitting. The results of measuring a test workpiece with the dimension of 24 mm × 12 mm × 2 mm through a single exposure show that the repeated measurement accuracy can reach 0.2 µm and the absolute accuracy can reach 0.5 µm. Compared with other methods, our method can achieve the large-field measurement through only one exposure and without the mechanical movement of cameras. The measurement precision is higher and the speed is faster.

Prediction of Pedestrian Crossing Behavior Based on Surveillance Video.

Prediction of pedestrian crossing behavior is an important issue faced by the realization of autonomous driving. The current research on pedestrian crossing behavior prediction is mainly based on vehicle camera. However, the sight line of vehicle camera may be blocked by other vehicles or the road environment, making it difficult to obtain key information in the scene. Pedestrian crossing behavior prediction based on surveillance video can be used in key road sections or accident-prone areas to provide supplementary information for vehicle decision-making, thereby reducing the risk of accidents. To this end, we propose a pedestrian crossing behavior prediction network for surveillance video. The network integrates pedestrian posture, local context and global context features through a new cross-stacked gated recurrence unit (GRU) structure to achieve accurate prediction of pedestrian crossing behavior. Applied onto the surveillance video dataset from the University of California, Berkeley to predict the pedestrian crossing behavior, our model achieves the best results regarding accuracy, F1 parameter, etc. In addition, we conducted experiments to study the effects of time to prediction and pedestrian speed on the prediction accuracy. This paper proves the feasibility of pedestrian crossing behavior prediction based on surveillance video. It provides a reference for the application of edge computing in the safety guarantee of automatic driving.

Robust Drivable Road Region Detection for Fixed-Route Autonomous Vehicles Using Map-Fusion Images.

Environment perception is one of the major issues in autonomous driving systems. In particular, effective and robust drivable road region detection still remains a challenge to be addressed for autonomous vehicles in multi-lane roads, intersections and unstructured road environments. In this paper, a computer vision and neural networks-based drivable road region detection approach is proposed for fixed-route autonomous vehicles (e.g., shuttles, buses and other vehicles operating on fixed routes), using a vehicle-mounted camera, route map and real-time vehicle location. The key idea of the proposed approach is to fuse an image with its corresponding local route map to obtain the map-fusion image (MFI) where the information of the image and route map act as complementary to each other. The information of the image can be utilized in road regions with rich features, while local route map acts as critical heuristics that enable robust drivable road region detection in areas without clear lane marking or borders. A neural network model constructed upon the Convolutional Neural Networks (CNNs), namely FCN-VGG16, is utilized to extract the drivable road region from the fused MFI. The proposed approach is validated using real-world driving scenario videos captured by an industrial camera mounted on a testing vehicle. Experiments demonstrate that the proposed approach outperforms the conventional approach which uses non-fused images in terms of detection accuracy and robustness, and it achieves desirable robustness against undesirable illumination conditions and pavement appearance, as well as projection and map-fusion errors.