With the development of infrared detection technology and the improvement of military remote sensing needs, infrared object detection networks with low false alarms and high detection accuracy have been a research focus. However, due to the lack of texture information, the false detection rate of infrared object detection is high, resulting in reduced object detection accuracy. To solve these problems, we propose an infrared object detection network named Dual-YOLO, which integrates visible image features. To ensure the speed of model detection, we choose the You Only Look Once v7 (YOLOv7) as the basic framework and design the infrared and visible images dual feature extraction channels. In addition, we develop attention fusion and fusion shuffle modules to reduce the detection error caused by redundant fusion feature information. Moreover, we introduce the Inception and SE modules to enhance the complementary characteristics of infrared and visible images. Furthermore, we design the fusion loss function to make the network converge fast during training. The experimental results show that the proposed Dual-YOLO network reaches 71.8% mean Average Precision (mAP) in the DroneVehicle remote sensing dataset and 73.2% mAP in the KAIST pedestrian dataset. The detection accuracy reaches 84.5% in the FLIR dataset. The proposed architecture is expected to be applied in the fields of military reconnaissance, unmanned driving, and public safety.

The potential of random pattern based computational ghost imaging (CGI) for real-time applications has been offset by its long image reconstruction time and inefficient reconstruction of complex diverse scenes. To overcome these problems, we propose a fast image reconstruction framework for CGI, called “DeepGhost”, using deep convolutional autoencoder network to achieve real-time imaging at very low sampling rates (10–20%). By transferring prior-knowledge from STL-10 dataset to physical-data driven network, the proposed framework can reconstruct complex unseen targets with high accuracy. The experimental results show that the proposed method outperforms existing deep learning and state-of-the-art compressed sensing methods used for ghost imaging under similar conditions. The proposed method employs deep architecture with fast computation, and tackles the shortcomings of existing schemes i.e., inappropriate architecture, training on limited data under controlled settings, and employing shallow network for fast computation.

Fourier single pixel imaging (FSPI) is well known for reconstructing high quality images but only at the cost of long imaging time. For real-time applications, FSPI relies on under-sampled reconstructions, failing to provide high quality images. In order to improve imaging quality of real-time FSPI, a fast image reconstruction framework based on deep learning (DL) is proposed. More specifically, a deep convolutional autoencoder network with symmetric skip connection architecture for real time 96 × 96 imaging at very low sampling rates (5–8%) is employed. The network is trained on a large image set and is able to reconstruct diverse images unseen during training. The promising experimental results show that the proposed FSPI coupled with DL (termed DL-FSPI) outperforms conventional FSPI in terms of image quality at very low sampling rates.

The integrated model of echo laser pulse profile (ELPP) of a target with arbitrary shape is studied under the condition of the ELPP affected by target and atmospheric turbulence simultaneously. The ELPPs of four typical targets (a plane, a cone, a sphere and an aspherical surface) are employed to test the validity of the model by analytical and numerical approaches. Based on simulations of the ELPP under different targets and atmospheric turbulence intensity, the results show a good agreement between two methods, and the ELPP of a target with discontinuous surface is more easily affected by atmospheric turbulence than that with a continuous surface. Besides that, we study the relationship between the number of grids and the relative error of analytical and numerical approaches, which are of interest to obtain the optimal number of grids used in the simulations.

Image fusion integrates information from multiple images (of the same scene) to generate a (more informative) composite image suitable for human and computer vision perception. The method based on multiscale decomposition is one of the commonly fusion methods. In this study, a new fusion framework based on the octave Gaussian pyramid principle is proposed. In comparison with conventional multiscale decomposition, the proposed octave Gaussian pyramid framework retrieves more information by decomposing an image into two scale spaces (octave and interval spaces). Different from traditional multiscale decomposition with one set of detail and base layers, the proposed method decomposes an image into multiple sets of detail and base layers, and it efficiently retains high- and low-frequency information from the original image. The qualitative and quantitative comparison with five existing methods (on publicly available image databases) demonstrate that the proposed method has better visual effects and scores the highest in objective evaluation.

Image dehazing is challenging due to the problem of ill-posed parameter estimation. Numerous prior-based and learning-based methods have achieved great success. However, most learning-based methods use the changes and connections between scale and depth in convolutional neural networks for feature extraction. Although the performance is greatly improved compared with the prior-based methods, the performance in extracting detailed information is inferior. In this paper, we proposed an image dehazing model built with a convolutional neural network and Transformer, called Transformer for image dehazing (TID). First, we propose a Transformer-based channel attention module (TCAM), using a spatial attention module as its supplement. These two modules form an attention module that enhances channel and spatial features. Second, we use a multiscale parallel residual network as the backbone, which can extract feature information of different scales to achieve feature fusion. We experimented on the RESIDE dataset, and then conducted extensive comparisons and ablation studies with state-of-the-art methods. Experimental results show that our proposed method effectively improves the quality of the restored image, and it is also better than the existing attention modules in performance.