NID-DETR: A novel model for accurate target detection in dark environments

Target detection in low-light conditions poses significant challenges due to reduced contrast, increased noise, and color distortion, all of which adversely affect detection accuracy and robustness. Effective low-light target detection is crucial for reliable vision in critical applications such as surveillance, autonomous driving, and underwater exploration. Current mainstream algorithms face challenges in extracting meaningful features under low-light conditions, which significantly limits their effectiveness. Furthermore, existing vision Transformer models demonstrate high computational complexity, indicating a need for further optimization and enhancement. Initially, we enhance the dataset during model training to optimize machine vision perception. Subsequently, we design an inverted residual cascade structure module to effectively address the inefficiencies in the global attention window mechanism. Finally, in the target detection output layer, we adopt strategies to reduce concatenation operations and optimize small object detection heads to decrease the model parameter count and improve precision. The dataset is divided into training, testing, and validation sets in a 7:2:1 ratio. Validation on the low-light dataset demonstrates a reduction of 27% in model parameters, with improvements of 2.4%, 4.8%, and 2% in AP_50:95, AP₅₀, and AP₇₅, respectively. Our model outperforms both the best baseline and other state-of-the-art models. These experimental results underscore the effectiveness of our proposed approach.