With the rapid development of remote sensing technology, optical remote sensing images are increasingly being used in areas such as military reconnaissance, environmental monitoring, and urban planning. Due to the small number of pixels, fuzzy features, and complex background, it is difficult for conventional convolutions to effectively extract features from small objects. To address this problem, we propose to use multi-scale dilated convolutions to increase the receptive field size of the model to adapt to changes in object size, capture multi-scale contextual information of the feature map, and extract richer object features. First, we propose a Dilated Convolutional Residual (DCR) module for high-level feature extraction in the network. Second, the context aggregation (CONTEXT) module uses remote interaction to perform associative computation on images using contextual aggregation, allowing the model to understand the global semantic information of the image. We propose a novel object detection method, DCN-YOLO, which achieves an AP50 of 56.6 on the AI-TOD dataset, effectively improving the detection accuracy and robustness of small objects in remote sensing images. It provides a new technical approach to the detection of small objects in remote sensing.

Underwater single-photon imaging is challenging, as the transmitting path presents turbulence and strong backscattering noise; both facts degrade the image, thus hindering its applications in real world. However, current studies on underwater single-photon modeling have generally overlooked the potential impact of water turbulence on imaging performance. This oversight may result in an inaccurate characterization of the optical propagation process in realistic imaging environment. This letter proposed a joint denoising and deblurring method with regularization by denoising (JDD-RED) for underwater single-photon image that include the modeling of turbulence and the tailored restoration model, improving the performance by considering blurring mechanism, as well as advanced signal processing method. This method is validated on numerical experiments by employing joint deblurring and denoising tasks. Compared with the PICK-3-D algorithm, the JDD-RED reconstruction results demonstrate that more detailed information can be retained while denoising. In addition, the results show an average improvement of 1.48 dB in peak signal-to-noise ratio (PSNR) and 60% in structural similarity (SSIM), proving the superior performance of the JDD-RED algorithm.

Lensless imaging represents a significant advancement in imaging technology, offering unique benefits over traditional optical systems due to its compact form factor, ideal for applications within the Internet of Things (IoT) ecosystem. Despite its potential, the intensive computational requirements of current lensless imaging reconstruction algorithms pose a challenge, often exceeding the resource constraints typical of IoT devices. To meet this challenge, a novel approach is introduced, merging multi-level image restoration with the pix2pix generative adversarial network architecture within the lensless imaging sphere. Building on the foundation provided by U-Net, a Multi-level Attention-based Lensless Image Restoration Network (MARN) is introduced to further augment the generator’s capabilities. In this methodology, images reconstructed through Tikhonov regularization are perceived as degraded images, forming the foundation for further refinement via the Pix2pix network. This process is enhanced by incorporating an attention-focused mechanism in the encoder--decoder structure and by implementing stage-wise supervised training within the deep convolutional network, contributing markedly to the improvement of the final image quality. Through detailed comparative evaluations, the superiority of the introduced method is affirmed, outperforming existing techniques and underscoring its suitability for addressing the computational challenges in lensless imaging within IoT environments. This method can produce excellent lensless image reconstructions when sufficient computational resources are available, and it consistently delivers optimal results across varying computational resource constraints. This algorithm enhances the applicability of lensless imaging in applications such as the Internet of Things, providing higher-quality image acquisition and processing capabilities for these domains.

光子计数激光雷达技术具有极高的探测灵敏度与时间分辨率，是极端条件下高精度目标信息获取的重要手段。由于该技术通过探测单光子级的回波能量实现对目标信息的三维重建，因此极易受噪声干扰，导致成像质量严重降低。基于高速电子门控的距离选通技术虽然可以有效抑制噪声，但存在参数设计依靠经验、目标检测区间窄等问题。本文提出了一种在宽目标检测区间条件下的目标信息提取及三维重建方法，首先通过对三维回波信息的获取机理及其概率模型进行分析，获取目标信息分布范围并通过算法门控提取有效信息；再采用高效的图像重建算法进一步提升三维重建的质量，从而具有比基于纯硬件的去噪方法更强的抑噪能力。实验结果显示，在平均像素光子数仅为3.020，且信号噪声比仅为0.106的极端条件下，本文提出的目标信息提取方法可将信号噪声比提升19.330倍；再配合高效的图像重建算法，距离图像的重建信噪比相比于传统的互相关算法提升了33.520dB，大幅提升了强噪声环境下高精度目标信息获取的能力。

Single photon 3D imaging is an emerging topic for optronic sensing under extreme scenarios (e.g. spaceborne altimeter, long range imaging). However, such technique suffers from low photon counts and strong noise, which is due to either strong attenuation from the environment or reduced acquisition time. Although state-of-the-art algorithms have been proposed to achieve high resolution results from corrupted single photon 3D data, the trade-off between the restoration performance and computational complexity remains challenging. This paper presents a fast and robust restoration approach for single photon 3D data, which adaptively smooth the sparse and noisy histogram by applying a parameterized kernel and finally reconstruct the 3D image using matched filter. The implementation can be fast as the core step of the processing is generalized as a 3D convolution that can be solved by Fast Fourier Transform (FFT). The method is validated on various conditions and scenarios from Middbury dataset and real data, where the proposed method showed robust results as the competing state-of-the-art algorithms with fast implementation.