All Projects → zhpmatrix → VisDrone2018

zhpmatrix / VisDrone2018

Licence: other
ECCV2018(Challenge-Object Detection in Images)

Programming Languages

python
139335 projects - #7 most used programming language
Roff
2310 projects
c
50402 projects - #5 most used programming language
Cuda
1817 projects
C++
36643 projects - #6 most used programming language
matlab
3953 projects
shell
77523 projects

Projects that are alternatives of or similar to VisDrone2018

VisDrone-dataset-python-toolkit
This repository provides a basic Pythonic toolkit for the VisDrone-Dataset (2018).
Stars: ✭ 30 (-65.12%)
Mutual labels:  faster-rcnn, visdrone
faster rcnn
Another pytorch implementation of Faster RCNN.
Stars: ✭ 24 (-72.09%)
Mutual labels:  faster-rcnn
Real-Time-Object-Detection-API-using-TensorFlow
A Transfer Learning based Object Detection API that detects all objects in an image, video or live webcam. An SSD model and a Faster R-CNN model was pretrained on Mobile net coco dataset along with a label map in Tensorflow. This model were used to detect objects captured in an image, video or real time webcam. Open CV was used for streaming obj…
Stars: ✭ 50 (-41.86%)
Mutual labels:  faster-rcnn
tf-faster-rcnn
Tensorflow 2 Faster-RCNN implementation from scratch supporting to the batch processing with MobileNetV2 and VGG16 backbones
Stars: ✭ 88 (+2.33%)
Mutual labels:  faster-rcnn
Object-and-Semantic-Part-Detection-pyTorch
Joint detection of Object and its Semantic parts using Attention-based Feature Fusion on PASCAL Parts 2010 dataset
Stars: ✭ 18 (-79.07%)
Mutual labels:  faster-rcnn
publications-tabelini-ijcnn-2019
Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural Images
Stars: ✭ 19 (-77.91%)
Mutual labels:  faster-rcnn
RefRESH
Create RefRESH data: dataset tools for Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation (ECCV 2018)
Stars: ✭ 51 (-40.7%)
Mutual labels:  eccv-2018
Faster-RCNN-LocNet
A simplified implementation of paper : Improved Localization Accuracy by LocNet for Faster R-CNN Based Text Detection
Stars: ✭ 25 (-70.93%)
Mutual labels:  faster-rcnn
frcnn-from-scratch-with-keras
💥Faster R-CNN from scratch written with Keras
Stars: ✭ 157 (+82.56%)
Mutual labels:  faster-rcnn
Faster-RCNN-Pytorch-Simple
No description or website provided.
Stars: ✭ 24 (-72.09%)
Mutual labels:  faster-rcnn
Object-Detection-And-Tracking
Target detection in the first frame and Tracking target by SiamRPN.
Stars: ✭ 33 (-61.63%)
Mutual labels:  faster-rcnn
Faster RCNN tensorflow
Implementation of Faster RCNN for Vehicle Detection
Stars: ✭ 16 (-81.4%)
Mutual labels:  faster-rcnn
Depth-VRD
Improving Visual Relation Detection using Depth Maps (ICPR 2020)
Stars: ✭ 33 (-61.63%)
Mutual labels:  faster-rcnn
semi-memory
Tensorflow Implementation on Paper [ECCV2018]Semi-Supervised Deep Learning with Memory
Stars: ✭ 49 (-43.02%)
Mutual labels:  eccv-2018
pytorch-faster-rcnn
No description or website provided.
Stars: ✭ 45 (-47.67%)
Mutual labels:  faster-rcnn
GIouloss CIouloss caffe
Caffe version Generalized & Distance & Complete Iou loss Implementation for Faster RCNN/FPN bbox regression
Stars: ✭ 42 (-51.16%)
Mutual labels:  faster-rcnn
lightDenseYOLO
A real-time object detection app based on lightDenseYOLO Our lightDenseYOLO is the combination of two components: lightDenseNet as the CNN feature extractor and YOLO v2 as the detection module
Stars: ✭ 20 (-76.74%)
Mutual labels:  faster-rcnn
Faster rcnn Cplusplus vs2013
faster-rcnn_VS2013with C++
Stars: ✭ 77 (-10.47%)
Mutual labels:  faster-rcnn
CFUN
Combining Faster R-CNN and U-net for efficient medical image segmentation
Stars: ✭ 109 (+26.74%)
Mutual labels:  faster-rcnn
object-tracking
Multiple Object Tracking System in Keras + (Detection Network - YOLO)
Stars: ✭ 89 (+3.49%)
Mutual labels:  faster-rcnn

VisDrone2018

说明:后续可能不更新了。

Tips: this repo will not be updated.

Baseline:

Name maxDets Result
Average Precision (AP) @( IoU=0.50:0.95) maxDets=500 15.8738%.
Average Precision (AP) @( IoU=0.50 ) maxDets=500 21.7822%.
Average Precision (AP) @( IoU=0.75 ) maxDets=500 17.1753%.
Average Recall (AR) @( IoU=0.50:0.95) maxDets= 1 0.83255%.
Average Recall (AR) @( IoU=0.50:0.95) maxDets= 10 7.1636%.
Average Recall (AR) @( IoU=0.50:0.95) maxDets=100 20.7602%.
Average Recall (AR) @( IoU=0.50:0.95) maxDets=500 20.7602%.

Cases From Test DataSet:

Implementation of a method of data augmentation named patching:

before augmentation:

aug1

after augmentation(only patching pedestrian and awning-tricycle, show pedestrian only):

aug0

ECCV2018的一个workshop举办的比赛,详见Vision Meets Drones: A Challenge.

VisDrone2018_Dev_Kit: 官方提供的针对数据集的工具,用于评测。可以改为其他工具,比如在图片上显示BBox;

Txt2XML: 官方给定数据集的Ground Truth是自己的标注方式(Txt),该工具将该标注方式转化为PASCAL VOC2007的标注方式(XML);Python实现;

ShowBBOXFromXML: 针对PASCAL VOC2007,在图片上显示BBox;Python实现;该工具已经和官方给定基于Matlab的代码做过准确度对比,检验通过;

数据集的Badcase: 将BBox画成一条线的,导致NaN错误,需要过滤,详情可以参考issues;

Code中分享了基于PyTorch的Faster R-CNN代码用于这个比赛,原始代码来自@jwyang,原始代码写的也有很多不完善的地方,但是是基于PyTorch实现的star最多的,用起来是没有问题的。Code中的仅仅作为该比赛代码的备份,不做正式分享。比如,没有数据。如果想要在现有代码基础上做些工作,可以联系我本人,帮助跑代码。

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].