The expansion of space exploration has led to a soar in the space debris population, increasing the risks of collisions. Addressing this challenge requires advanced space surveillance technologies. Traditional
Object detection serves as a key component of computer vision tasks, primarily focused on accurately identifying and localizing various objects within an image. Object detection techniques are categorized into two groups such as conventional object detectors and object detectors based on deep learning (DL...
Some other examples are using DCT coefficients (Ozer & Wolf, 2002), utilizing partial-impediment taking care of body-part detectors (Mohan et al., 2001) or the block-based system by Utsumi and Tetsutani (2002). All these methods use a bounding box for detecting humans from the background...
YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023), pp. 17-24 Google Scholar [40] K. Ren, L.D. Chang, M.J. Wan, et al. An improved U-net-based retinal ves...
I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors,目录传统的去雾方法1.SingleImageHazeRemovalUsingDarkChannelPrior何凯明2009CVPR2.AFastSingleImageHazeRemovalAlgorithmUsingColorAttenuationPrior2015TIP基于深度学习的图像去雾
Accurate, fast and lightweight dense target detection methods are highly important for precision agriculture. To detect dense apricot flowers using drones, we propose an improved dense target detection method based on YOLOv8, named D-YOLOv8. First, we in
First, current prevailing detectors exploit either overlap- based [29, 26] or distance-based [31] strategies to select the positive priors of objects for training. However, small instances usually occupy an extremely limited area, there- fore the regi...
One-stage detector: The most representative one-stage detectors are Y- OLO [24,25] and SSD [22]. They predict confidences and locations for multiple RFB Net for Accurate and Fast Object Detection 5 objects based on the whole feature map. Both the detectors adopt lightweight backbones for ...
these detectors are cost-effective, as they only require one type of sensor, significantly reducing hardware and maintenance costs. Single-modality detectors can also focus on leveraging the strengths of a specific sensor, such as the precision of LiDAR in depth estimation or the rich visual detai...
Traditional object detectors based on deep learning rely on plenty of labeled samples, which are expensive to obtain. Few-shot object detection (FSOD) attempts to solve this problem, learning detection objects from a few labeled samples, but the performance is often unsatisfactory due to the scarci...