The perception of drones, also known as Unmanned Aerial Vehicles (UAVs), particularly in infrared videos, is crucial for effective anti-UAV tasks. However, existing datasets for UAV tracking have limitations in terms of target size and attribute distribution characteristics, which do not fully represent complex realistic scenes. To address this issue, we introduce a generalized infrared UAV tracking benchmark called Anti-UAV410 . The benchmark comprises a total of 410 videos with over 438 K manually annotated bounding boxes. To tackle the challenges of UAV tracking in complex environments, we propose a novel method called Siamese drone tracker ( SiamDT ). SiamDT incorporates a dual-semantic feature extraction mechanism that explicitly models targets in dynamic background clutter, enabling effective tracking of small UAVs. The SiamDT method consists of three key steps: Dual-Semantic RPN Proposals (DS-RPN) , Versatile R-CNN (VR-CNN) , and Background Distractors Suppression . These steps are responsible for generating candidate proposals, refining prediction scores based on dual-semantic features, and enhancing the discriminative capacity of the trackers against dynamic background clutter, respectively. Extensive experiments conducted on the Anti-UAV410 dataset and three other large-scale benchmarks demonstrate the superior performance of the proposed SiamDT method compared to recent state-of-the-art trackers.

Benefitting from insensitivity to light and high penetration of foggy environments, infrared cameras are widely used for sensing in nighttime traffic scenes. However, the low contrast and lack of chromaticity of thermal infrared (TIR) images hinder the human interpretation and portability of high-level computer vision algorithms. Colorization to translate a nighttime TIR image into a daytime color (NTIR2DC) image may be a promising way to facilitate nighttime scene perception. Despite recent impressive advances in image translation, semantic encoding entanglement and geometric distortion in the NTIR2DC task remain under-addressed. Hence, we propose a toP-down attEntion And gRadient aLignment based generative adversarial network, referred to as PearlGAN. A top-down guided attention module and an elaborate attentional loss are first designed to reduce the semantic encoding ambiguity during translation. Then, a structured gradient alignment loss is introduced to encourage edge consistency between the translated and input images. In addition, pixel-level annotation is carried out on a subset of FLIR and KAIST datasets to evaluate the semantic preservation performance of multiple translation methods. Furthermore, a new metric is devised to evaluate the geometric consistency in the translation process. Extensive experiments demonstrate the superiority of the proposed PearlGAN over other image translation methods for the NTIR2DC task. The source code and labeled segmentation masks will be available at https://github.com/FuyaLuo/PearlGAN/ .

Gamma rhythms in many brain regions, including the primary visual cortex (V1), are thought to play a role in information processing. Here, we report a surprising finding of 3 narrowband gamma rhythms in V1 that processed distinct spatial frequency (SF) signals and had different neural origins. The low gamma (LG; 25 to 40 Hz) rhythm was generated at the V1 superficial layer and preferred a higher SF compared with spike activity, whereas both the medium gamma (MG; 40 to 65 Hz), generated at the cortical level, and the high gamma HG; (65 to 85 Hz), originated precortically, preferred lower SF information. Furthermore, compared with the rates of spike activity, the powers of the 3 gammas had better performance in discriminating the edge and surface of simple objects. These findings suggest that gamma rhythms reflect the neural dynamics of neural circuitries that process different SF information in the visual system, which may be crucial for multiplexing SF information and synchronizing different features of an object.