LiuDongdong

爱好由来落笔难,一诗千改心始安。

Deformable_conv

Dai J, Qi H, Xiong Y, et al. Deformable convolutional networks[C]//Proceedings of the IEEE international conference on computer vision. 2017: 764-773. [code 3.6k] Paper: Deformable Conv Summary introduce two new modules to enhance the transformation modeling capability of CNNS, deformable convolution and deformable RoI pooling, based on the idea of augmenting the spatial and learning the offsets from the target tasks without supervision. Research Objective Application Area: Purpose: Proble Statement

PointCloud Record

3D数据通常可以用不同的格式表示,包括深度图像,点云,网格和体积网格。 作为一种常用格式,点云表示将原始几何信息保留在3D空间中,而不会进行任

树莓派车牌识别

检测到车牌&识别每个车牌边界框内的文本。 1. 硬件设计 2. 模型选择 Yolo3: https://github.com/experiencor/keras-yolo3 https://github.com/ThorPham/License-plate-detection CRAFT & CRNN: https://github.com/faustomorales/keras-ocr 首先,YOLOv3 模型从摄像机处接收到一帧帧图像,然后在每
0%