Chen Bing's Projects
PyTorch ,ONNX and TensorRT implementation of YOLOv4
RAIM(Receiver Autonomous Integrity Monitoring)
RAIM for PANG NAV a tool for processing GNSS measurements in SPP, including RAIM functionality
R-CNN: Regions with Convolutional Neural Network Features
Semi-direct Visual Odometry
RTCM3.3
Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!
Kalman filters (KF, EKF, UKF), LIDAR object detection
A toy library for Structure from Motion using OpenCV
This is a fast caffe implementation of ShuffleNet.
ShuffleNet in PyTorch. Based on https://arxiv.org/abs/1707.01083
SLAM related matlab
SLAM related papers and mathematical materials
Track Advancement of SLAM 跟踪SLAM前沿动态【ICRA2019已更】
Algorithms and simulations on spoofing detection.
Single Shot MultiBox Detector in TensorFlow
Containing a wrapper for libviso2, a visual odometry library. The project about Optical flow and ORB and Libviso = visual odometry
Computation using data flow graphs for scalable machine learning
记录自己学习TensorFlow的笔记和代码
VGG19 and VGG16 on Tensorflow
🔥 Pure tensorflow Implement of YOLOv3 with support to train your own dataset
Sliding-window object detectors that generate boundingbox object predictions over a dense, regular grid have advanced rapidly and proven popular. In contrast, modern instance segmentation approaches are dominated by methods that first detect object bounding boxes, and then crop and segment these regions, as popularized by Mask R-CNN. In this work, we investigate the paradigm of dense slidingwindow instance segmentation, which is surprisingly underexplored. Our core observation is that this task is fundamentally different than other dense prediction tasks such as semantic segmentation or bounding-box object detection, as the output at every spatial location is itself a geometric structure with its own spatial dimensions. To formalize this, we treat dense instance segmentation as a prediction task over 4D tensors and present a general framework called TensorMask that explicitly captures this geometry and enables novel operators on 4D tensors. We demonstrate that the tensor view leads to large gains over baselines that ignore this structure, and leads to results comparable to Mask R-CNN. These promising results suggest that TensorMask can serve as a foundation for novel advances in dense mask prediction and a more complete understanding of the task. Code will be made available.
Tensorflow Faster RCNN for Object Detection
Real-time generic object detection on mobile platforms is a crucial but challenging computer vision task. However, previous CNN-based detectors suffer from enormous computational cost, which hinders them from real-time inference in computation-constrained scenarios. In this paper, we investigate the effectiveness of two-stage detectors in real-time generic detection and propose a lightweight twostage detector named ThunderNet. In the backbone part, we analyze the drawbacks in previous lightweight backbones and present a lightweight backbone designed for object detection. In the detection part, we exploit an extremely efficient RPN and detection head design. To generate more discriminative feature representation, we design two efficient architecture blocks, Context Enhancement Module and Spatial Attention Module. At last, we investigate the balance between the input resolution, the backbone, and the detection head. Compared with lightweight one-stage detectors, ThunderNet achieves superior performance with only 40% of the computational cost on PASCAL VOC and COCO benchmarks. Without bells and whistles, our model runs at 24.1 fps on an ARM-based device. To the best of our knowledge, this is the first real-time detector reported on ARM platforms. Code will be released for paper reproduction.
Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usage
多旋翼无人机组合导航系统-多源信息融合算法
**科学院大学研一课程课件共享项目University of Chinese Academy of Sciences postgraduate course textbook sharing project