# An object measurement method based on BCNet
For copyright reasons, only part of the code is provided here,The main codes are from the website:https://github.com/lkeab/BCNet.
## Highlights
- **BCNet:** Two/one-stage (detect-then-segment) instance segmentation with state-of-the-art performance.
- **Novelty:** A new mask head design, explicit occlusion modeling with **bilayer decouple (object boundary and mask)** for the occluder and occludee in the same RoI.
- **Efficacy:** Large improvements both the FCOS (anchor-free) and Faster R-CNN (anchor-based) detectors.
- **Simple:** Small additional computation burden and easy to use.
Visualization of Occluded Objects
-----------------
<table>
<tr>
<td><center><img src="figures/fig_vis2_new.png" height="260">
Qualitative instance segmentation results of our BCNet, using ResNet-101-FPN and Faster R-CNN detector. The bottom row visualizes squared heatmap of **object contour and mask predictions** by the two GCN layers for the occluder and occludee in **the same ROI region** specified by the red bounding box, which also makes the final segmentation result of BCNet more explainable than previous methods. The heatmap visualization of GCN-1 in fourth column example shows that **BCNet handles multiple occluders with in the same RoI by grouping them together**. See our paper for more visual examples and comparisons.
</center></td>
</tr>
</table>
Visualization of Occluded Bolts and Shims
-----------------
<table>
<tr>
<td><center><img src="result_img/0114.jpg" height="540">
The segmentation results of bolts and Shims using bcnet are shown in the figure,It can be seen that there is a good segmentation effect for occluded objects, which is the key to the next step of measurement
</center></td>
</tr>
</table>
Software Interface
-----------------
<table>
<tr>
<td><center><img src="interface.jpg" height="540">
The interface is shown in the figure. It displays the status of the program and can also detect the status of the equipment. The picture captured by the camera will be displayed in the blank on the right side of the interface
</center></td>
</tr>
</table>
Main Code Structure
-----------------
<table>
<tr>
<td><center><img src="code.jpg" height="540">
The main code structure of the measurement part is shown in the figure above. Most of the codes are not provided on the website, so the project can not run smoothly directly. If you are interested in this, please contact me.
</center></td>
</tr>
</table>
## Step-by-step Installation
```
conda create -n bcnet python=3.7 -y
source activate bcnet
conda install pytorch==1.4.0 torchvision==0.5.0 cudatoolkit=10.1 -c pytorch
# FCOS and coco api and visualization dependencies
pip install ninja yacs cython matplotlib tqdm
pip install opencv-python==4.4.0.40
# Boundary dependency
pip install scikit-image
export INSTALL_DIR=$PWD
# install pycocotools. Please make sure you have installed cython.
cd $INSTALL_DIR
git clone https://github.com/cocodataset/cocoapi.git
cd cocoapi/PythonAPI
python setup.py build_ext install
# install BCNet
cd $INSTALL_DIR
git clone https://github.com/lkeab/BCNet.git
cd BCNet/
python3 setup.py build develop
unset INSTALL_DIR
```
##
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码 机器人大赛参赛作品,供参赛人员参考,含设计文档,设计源码
资源推荐
资源详情
资源评论
收起资源包目录
中国机器人大赛-先进视觉赛-工业测量.zip (614个子文件)
configs 64B
ROIAlignRotated_cpu.cpp 16KB
ROIAlign_cpu.cpp 14KB
vision.cpp 3KB
nms_rotated_cpu.cpp 2KB
box_iou_rotated_cpu.cpp 1KB
deform_conv_cuda_kernel.cu 43KB
deform_conv_cuda.cu 32KB
ROIAlignRotated_cuda.cu 13KB
ROIAlign_cuda.cu 13KB
nms_rotated_cuda.cu 5KB
box_iou_rotated_cuda.cu 3KB
cuda_version.cu 134B
.gitignore 7B
box_iou_rotated_utils.h 9KB
deform_conv.h 8KB
ROIAlign.h 3KB
ROIAlignRotated.h 3KB
nms_rotated.h 976B
box_iou_rotated.h 887B
0276.jpg 194KB
interface.jpg 113KB
0125.jpg 109KB
0125.jpg 108KB
0120.jpg 93KB
0120.jpg 89KB
0051.jpg 81KB
0051.jpg 81KB
0048.jpg 73KB
0048.jpg 73KB
0001.jpg 72KB
0002.jpg 69KB
code.jpg 65KB
0003.jpg 65KB
0114.jpg 59KB
0114.jpg 58KB
0001.json 540KB
0002.json 530KB
0003.json 449KB
LICENSE 1KB
Makefile 650B
datasets.md 10KB
benchmarks.md 9KB
models.md 5KB
install.md 5KB
compatibility.md 4KB
data_loading.md 4KB
deployment.md 3KB
getting_started.md 3KB
README.md 3KB
extend.md 2KB
contributing.md 2KB
configs.md 2KB
write-models.md 2KB
evaluation.md 2KB
training.md 1KB
README.md 1KB
changelog.md 497B
README.md 417B
README.md 364B
README.md 347B
README.md 326B
README.md 175B
README.md 122B
PKG-INFO 345B
fig_vis2_new.png 431KB
fig_vis1_new.png 380KB
netcompare.png 185KB
framework_new.png 122KB
lvis_v0_5_categories.py 218KB
visualizer.py 44KB
namesgenerator.py 31KB
roi_heads.py 30KB
shared.py 28KB
defaults.py 26KB
encoders.py 26KB
coco.py 26KB
process_dataset.py 24KB
fcos.py 23KB
process_dataset_occ.py 20KB
caffe2_modeling.py 20KB
coco_evaluation.py 20KB
mask_head.py 20KB
rpn_outputs.py 19KB
retinanet.py 18KB
rotated_boxes.py 18KB
defaults.py 18KB
c10.py 18KB
detection_utils.py 17KB
senet.py 17KB
masks.py 16KB
deform_conv.py 15KB
resnet.py 15KB
efficient_net.py 15KB
fast_rcnn.py 15KB
builtin_meta.py 15KB
transform_gen.py 15KB
hooks.py 15KB
build.py 14KB
c2_model_loading.py 14KB
共 614 条
- 1
- 2
- 3
- 4
- 5
- 6
- 7
资源评论
- Yuking0042024-03-05资源内容详细全面,与描述一致,对我很有用,有一定的使用价值。
- 长剑凌清秋2024-04-11资源内容总结地很全面,值得借鉴,对我来说很有用,解决了我的燃眉之急。
- m0_742071992024-04-10非常有用的资源,可以直接使用,对我很有用,果断支持!
- m0_738662912024-04-25资源是宝藏资源,实用也是真的实用,感谢大佬分享~
辣椒种子
- 粉丝: 3414
- 资源: 5723
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功