Remote sensing can efficiently acquire information and is widely used in many areas. Object detection is a key component in most applications. But complex backgrounds in remote sensing images severely degrade detection performance. Current methods fail to effectively suppress background interference while maintaining fast detection speeds. This paper proposes Attention-Guided Yolo (AG-Yolo), an efficient oriented object detection (OOD) method tailored for remote sensing. AG-Yolo incorporates an additional rotation parameter into the head of Yolo-v10 and extends its dual label assignment strategy to maintain high efficiency in OOD. An attention branch is further introduced to generate attention maps from shallow input features, guiding feature aggregation to focus on foreground objects and suppress complex background interference. Additionally, derived from the background complexity, a three-stage curriculum learning strategy is designed to train the model from some much easier samples generated from the labeled data. This approach can give the model a better starting point, improving its ability to handle complicated datasets and increasing detection precision. On the DOTA-v1.0 and DOTA-v1.5 datasets, compared with other advanced methods, our algorithm reduces the processing latency from 33.8 ms to 19.7 ms (a roughly 40% decrease) and produces a certain degree of improvement in the mAP metric.

The technology of infrared dim- and small-target detection is irreplaceable in many fields, such as those of missile early warning systems and forest fire prevention, among others. However, numerous components interfere with infrared imaging, presenting challenges for achieving successful detection of infrared dim and small targets with a low rate of false alarms. Hence, we propose a new infrared dim- and small-target detection network, Multiscale Feature Extraction U-Net for Infrared Dim- and Small-Target Detection (MFEU-Net), which can accurately detect targets in complex backgrounds. It uses the U-Net structure, and the encoders and decoders consist of ReSidual U-block and Inception, allowing rich multiscale feature information to be extracted. Thus, the effectiveness of algorithms in detecting very small-sized targets can be improved. In addition, through the multidimensional channel and spatial attention mechanism, the model can be adjusted to focus more on the target area in the image, improving its extraction of target information and detection performance in different scenarios. The experimental results show that our proposed algorithm outperforms other advanced algorithms in detection performance. On the MFIRST, SIRST, and IRSTD-1k datasets, we achieved detection rates of 0.864, 0.962, and 0.965; IoU values of 0.514, 0.671, and 0.630; and false alarm rates of 3.08 × ${10}^{-5}$, 2.61 × ${10}^{-6}$, and 1.81 × ${10}^{-5}$, respectively.

Low-light images are prevalent in intelligent monitoring and many other applications, with low brightness hindering further processing. Although low-light image enhancement can reduce the influence of such problems, current methods often involve a complex network structure or many iterations, which are not conducive to their efficiency. This paper proposes a Zero-Reference Camera Response Network using a camera response model to achieve efficient enhancement for arbitrary low-light images. A double-layer parameter-generating network with a streamlined structure is established to extract the exposure ratio $\mathbf{K}$ from the radiation map, which is obtained by inverting the input through a camera response function. Then, $\mathbf{K}$ is used as the parameter of a brightness transformation function for one transformation on the low-light image to realize enhancement. In addition, a contrast-preserving brightness loss and an edge-preserving smoothness loss are designed without the requirement for references from the dataset. Both can further retain some key information in the inputs to improve precision. The enhancement is simplified and can reach more than twice the speed of similar methods. Extensive experiments on several LLIE datasets and the DARK FACE face detection dataset fully demonstrate our method’s advantages, both subjectively and objectively.

Infrared target detection has a wide range of application value, but due to the characteristics of infrared images, infrared targets are easily submerged in the complex background. Therefore, in complex scenes, it is difficult to effectively and accurately detect infrared dim small targets. For this reason, we design an infrared dim small target (IDST) detection algorithm containing Large-size Receptive Fields (LRFNet). It uses the Residual network with an Inverted Pyramid Structure (RIPS), which consists of convolutional layers that become progressively smaller, so it can have a larger effective receptive field and can improve the robustness of the model. In addition, through the Attention Mechanisms with Large Receptive Fields and Inverse Bottlenecks (LRIB), it can make the network better localize the region where the target is located and improve the detection effect of the model. The experimental results show that our proposed algorithm outperforms other state-of-the-art algorithms in all evaluation metrics.

Under low-illumination conditions, the quality of the images collected by the sensor is significantly impacted, and the images have visual problems such as noise, artifacts, and brightness reduction. Therefore, this paper proposes an effective network based on Retinex for low-illumination image enhancement. Inspired by Retinex theory, images are decomposed into two parts in the decomposition network, and sent to the sub-network for processing. The reconstruction network constructs global and local residual convolution blocks to denoize the reflection component. The enhancement network uses frequency information, combined with attention mechanism and residual density network to enhance contrast and improve the details of the illumination component. A large number of experiments on public datasets show that our method is superior to existing methods in both quantitative and visual aspects.