Long-distance infrared target detection technology utilizes infrared detection systems to accurately capture targets, demonstrating significant potential in aerospace fields such as space target detection and battlefield reconnaissance. In practical applications of infrared imaging, numerous engineering challenges arise, such as stray light, detector thermal conduction, and structural radiation. These complex interference factors can cause non-uniform backgrounds in images, affecting image quality and target detection accuracy. Additionally, when the imaging distance is long, the target appears small, with weak signal strength and unclear characteristics, which may result in detection failure due to interference. Therefore, this paper addresses the issues of complex backgrounds interference and weak targets in space infrared images by developing a method for Infrared dim and small target detection based on intelligent suppression method for complex backgrounds. This research provides new solutions for infrared target detection applications in complex backgrounds.This paper designs a method for detecting dim and small infrared targets based on intelligent suppression of complex backgrounds. The infrared scene-optimized encoder-decoder background suppression network model is designed to efficiently suppress complex backgrounds (Fig.2). A combination of multiple loss functions is employed to enhance the robustness of background reconstruction (Eq.14). The weak target detection task is accomplished using a threshold segmentation method (Eq.9). The effectiveness of the method is validated through four evaluation metrics: background standard deviation, target signal-to-noise ratio, detection rate, and false alarm rate (Fig.5, Tab.3-Tab.6).The experimental results were obtained on four infrared weak target datasets. The background suppression results of different detection methods on the test images are shown in Fig.5. The results obtained by the proposed method using the infrared scene-optimized encoder-decoder background suppression model show a significant reduction in background noise, with no false alarm targets, far surpassing the comparative methods. Table 3-Table 6 calculate four evaluation metrics: background standard deviation, target signal-to-noise ratio, detection rate, and false alarm rate. The background standard deviation decreased from 20.1463 to 1.8450, the signal-to-noise ratio increased from 2.2686 to 25.1897, the detection rate reached 0.9986, and the false alarm rate was 0.1824. The proposed method demonstrates superior performance in suppressing complex background interference and target detection compared to other methods.In the field of infrared long-distance weak target detection, due to complex interference such as stray light, detector heat conduction, and flash blind pixels, the background of infrared images often appears non-uniform. At the same time, the target imaging size is small and lacks obvious shape and texture features, which increases the difficulty of detection and recognition. Traditional feature extraction methods are prone to a large number of false alarms. Deep learning methods have advantages in feature extraction, but they are difficult to train under complex background interference. This paper combines the background reconstruction problem in the field of computer vision with the task of infrared image weak target detection, and proposes an infrared weak target detection method based on complex background intelligent suppression. This method uses the encoder-decoder architecture to design an infrared scene optimized encoding and decoding background suppression network model, introduces a multi-level fusion mechanism and a residual fusion module to achieve multi-scale feature extraction and multi-level feature fusion, and proposes a perceptual consistency loss function to improve the robustness of background reconstruction. Background suppression is effectively achieved through the background residual offset strategy, and finally the weak target detection task is completed by combining global threshold segmentation. Experimental results show that compared with the comparison method, the background standard deviation of this method in background suppression is reduced by up to 43.41%, and the target signal-to-noise ratio is increased to 110.0257. In terms of target detection, the detection rates in the four sets of data all exceeded 95%, demonstrating excellent detection results and strong engineering practicality, providing a new solution for infrared dim target detection tasks under complex backgrounds.