From 2b75cf9979b7b91061b41255b8573c1e47887abd Mon Sep 17 00:00:00 2001 From: Ngo Trung Date: Thu, 19 Aug 2021 17:40:39 +0900 Subject: [PATCH] GSOC2021: update readme files for all components --- .../BodyHandJointsDetector/README.md | 24 +++++++++---- .../imageBasedGestureRecognition/README.md | 34 +++++++++--------- .../poseBasedGestureRecognition/README.md | 35 ++++++++++--------- .../bodyHandJointsDetectorClient/README.md | 35 +++++++++++-------- .../README.md | 35 +++++++++++-------- .../README.md | 29 ++++++++------- 6 files changed, 107 insertions(+), 85 deletions(-) diff --git a/components/detection/BodyHandJointsDetector/README.md b/components/detection/BodyHandJointsDetector/README.md index 2e8d8daf..79759ad0 100644 --- a/components/detection/BodyHandJointsDetector/README.md +++ b/components/detection/BodyHandJointsDetector/README.md @@ -1,5 +1,5 @@ # BodyHandJointsDetector -Intro to component here +Body and hand detection: I apply the lightweight Openpose model, MediaPipe library, and the optical flow algorithm. The combination can process in real-time and with a lightweight model, so it is suitable for edge devices. ## Configuration parameters @@ -7,10 +7,15 @@ As any other component, *BodyHandJointsDetector* needs a configuration file to s ``` etc/config ``` -you can find an example of a configuration file. We can find there the following lines: -``` -EXAMPLE HERE -``` + +The configuration is already set, if changing the port of this component, please change to the same port in this component's client +[link](https://github.com/robocomp/robocomp-robolab/tree/master/components/detection/test/bodyHandJointsDetectorClient) + + +The setting for python enviroment can be found [here](https://robocomp.github.io/web/gsoc/2021/posts/trung_ngo_tan/post04) + + +Copy pretrained model from this [link](https://drive.google.com/file/d/1W3Ud3u_55pJ0V4ODs47pne_OUKTDLkQa/view?usp=sharing) to src/_model/ in the detector component folder. ## Starting the component To avoid changing the *config* file in the repository, we can copy it to the component's home directory, so changes will remain untouched by future git pulls: @@ -22,8 +27,15 @@ cd cp etc/config config ``` +Need to CMAKE the code with this command: + +``` +cmake . +``` + After editing the new config file we can run the component: ``` -bin/BodyHandJointsDetector config +python src/BodyHandJointsDetector.py etc/config ``` + diff --git a/components/detection/imageBasedGestureRecognition/README.md b/components/detection/imageBasedGestureRecognition/README.md index 8ec0d901..82544c1d 100644 --- a/components/detection/imageBasedGestureRecognition/README.md +++ b/components/detection/imageBasedGestureRecognition/README.md @@ -1,29 +1,29 @@ -# ImageBasedGestureRecognition -Intro to component here - +# ImageBasedRecognition +In this project, we implement [WLASL recognizer](https://github.com/dxli94/WLASL). There are pretrained model for this dataset. Therefore, we reuse these models without any training. +In the image-based approach, they use I3D model for recognition. Please follow instruction in this blog for updating the WLASL models [link](https://robocomp.github.io/web/gsoc/2021/posts/trung_ngo_tan/post05). ## Configuration parameters -As any other component, *ImageBasedGestureRecognition* needs a configuration file to start. In -``` -etc/config -``` -you can find an example of a configuration file. We can find there the following lines: -``` -EXAMPLE HERE -``` + +The configuration is already set, if changing the port of this component, please change to the same port in this component's client +[link](https://github.com/robocomp/robocomp-robolab/tree/master/components/detection/test/imageBasedGestureRecognitionClient) + + +The setting for python enviroment can be found [here](https://robocomp.github.io/web/gsoc/2021/posts/trung_ngo_tan/post04) + + +Copy pretrained model from this [link](https://drive.google.com/file/d/1VnCSZHCt69Cah7Xvf2D7P2Lfsx3L1Mqh/view?usp=sharing) to src/_model/ in the detector component folder. ## Starting the component -To avoid changing the *config* file in the repository, we can copy it to the component's home directory, so changes will remain untouched by future git pulls: + + +Need to CMAKE the code with this command: ``` -cd -``` -``` -cp etc/config config +cmake . ``` After editing the new config file we can run the component: ``` -bin/ImageBasedGestureRecognition config +python src/ImageBasedGestureRecognition.py etc/config ``` diff --git a/components/detection/poseBasedGestureRecognition/README.md b/components/detection/poseBasedGestureRecognition/README.md index 5a544539..638d5592 100644 --- a/components/detection/poseBasedGestureRecognition/README.md +++ b/components/detection/poseBasedGestureRecognition/README.md @@ -1,29 +1,30 @@ -# PoseBasedGestureRecognition -Intro to component here - +# PoseBasedRecognition +For pose-based reocngition, we reuse Pose-TGCN (graph neural network). This model have body/hand joints input and output the gesture classes. ## Configuration parameters -As any other component, *PoseBasedGestureRecognition* needs a configuration file to start. In -``` -etc/config -``` -you can find an example of a configuration file. We can find there the following lines: -``` -EXAMPLE HERE -``` + + +The configuration is already set, if changing the port of this component, please change to the same port in this component's client +[link](https://github.com/robocomp/robocomp-robolab/tree/master/components/detection/test/poseBasedGestureRecognitionClient) + + +The setting for python enviroment can be found [here](https://robocomp.github.io/web/gsoc/2021/posts/trung_ngo_tan/post04) + + +Copy pretrained model from this [link](https://drive.google.com/file/d/1noNAokd8a39a1_DbOjLn5Hdi9LsI4snr/view) to src/_model/ in the detector component folder. ## Starting the component -To avoid changing the *config* file in the repository, we can copy it to the component's home directory, so changes will remain untouched by future git pulls: + + +Need to CMAKE the code with this command: ``` -cd -``` -``` -cp etc/config config +cmake . ``` After editing the new config file we can run the component: ``` -bin/PoseBasedGestureRecognition config +python src/PoseBasedGestureRecognition.py etc/config ``` + diff --git a/components/detection/test/bodyHandJointsDetectorClient/README.md b/components/detection/test/bodyHandJointsDetectorClient/README.md index dd5d4be9..a690238c 100644 --- a/components/detection/test/bodyHandJointsDetectorClient/README.md +++ b/components/detection/test/bodyHandJointsDetectorClient/README.md @@ -1,29 +1,34 @@ # BodyHandJointDetectorClient -Intro to component here +This is a test client for [BodyHandJointDetector component](https://github.com/robocomp/robocomp-robolab/tree/master/components/detection/BodyHandJointsDetector). ## Configuration parameters -As any other component, *BodyHandJointDetectorClient* needs a configuration file to start. In -``` -etc/config -``` -you can find an example of a configuration file. We can find there the following lines: -``` -EXAMPLE HERE -``` +Follow the instruction in the main component for installation. ## Starting the component -To avoid changing the *config* file in the repository, we can copy it to the component's home directory, so changes will remain untouched by future git pulls: + +Need to CMAKE the code with this command: ``` -cd -``` -``` -cp etc/config config +cmake . ``` After editing the new config file we can run the component: +1) Run the main component: ``` -bin/BodyHandJointDetectorClient config +cd ../../BodyHandJointsDetector +python src/BodyHandJointsDetector.py etc/config ``` + +2) Run the client: +``` +cd ../test/bodyHandJointsDetectorClient +python src/BodyHandJointDetectorClient.py etc/config +``` + + +## DEMO: + +[![Youtube link](https://robocomp.github.io/web/gsoc/2021/posts/trung_ngo_tan/images/handbodyPoseYoutube.png)](https://www.youtube.com/watch?v=qpOU7or_zx8) + diff --git a/components/detection/test/imageBasedGestureRecognitionClient/README.md b/components/detection/test/imageBasedGestureRecognitionClient/README.md index a3269a03..1105ddda 100644 --- a/components/detection/test/imageBasedGestureRecognitionClient/README.md +++ b/components/detection/test/imageBasedGestureRecognitionClient/README.md @@ -1,29 +1,34 @@ # ImageBasedGestureRecognitionClient -Intro to component here +This is a test client for [ImageBasedGestureRecognition component](https://github.com/robocomp/robocomp-robolab/tree/master/components/detection/imageBasedGestureRecognition). ## Configuration parameters -As any other component, *ImageBasedGestureRecognitionClient* needs a configuration file to start. In -``` -etc/config -``` -you can find an example of a configuration file. We can find there the following lines: -``` -EXAMPLE HERE -``` +Follow the instruction in the main component for installation. ## Starting the component -To avoid changing the *config* file in the repository, we can copy it to the component's home directory, so changes will remain untouched by future git pulls: + +Need to CMAKE the code with this command: ``` -cd -``` -``` -cp etc/config config +cmake . ``` After editing the new config file we can run the component: +1) Run the main component: ``` -bin/ImageBasedGestureRecognitionClient config +cd ../../imageBasedGestureRecognition +python src/ImageBasedGestureRecognition.py etc/config ``` + +2) Run the client: +``` +cd ../test/imageBasedGestureRecognitionClient +python src/ImageBasedGestureRecognitionClient.py etc/config +``` + + +## DEMO: + +[![Youtube link](https://robocomp.github.io/web/gsoc/2021/posts/trung_ngo_tan/images/imagebasedRecognitionYoutube.png)](https://www.youtube.com/watch?v=aAywMZqqlVw) + diff --git a/components/detection/test/poseBasedGestureRecognitionClient/README.md b/components/detection/test/poseBasedGestureRecognitionClient/README.md index e5b88fff..721f6a61 100644 --- a/components/detection/test/poseBasedGestureRecognitionClient/README.md +++ b/components/detection/test/poseBasedGestureRecognitionClient/README.md @@ -1,29 +1,28 @@ # PoseBasedGestureRecognitionClient -Intro to component here +This is a test client for [PoseBasedGestureRecognition component](https://github.com/robocomp/robocomp-robolab/tree/master/components/detection/PoseBasedGestureRecognition). ## Configuration parameters -As any other component, *PoseBasedGestureRecognitionClient* needs a configuration file to start. In -``` -etc/config -``` -you can find an example of a configuration file. We can find there the following lines: -``` -EXAMPLE HERE -``` +Follow the instruction in the main component for installation. ## Starting the component -To avoid changing the *config* file in the repository, we can copy it to the component's home directory, so changes will remain untouched by future git pulls: + +Need to CMAKE the code with this command: ``` -cd -``` -``` -cp etc/config config +cmake . ``` After editing the new config file we can run the component: +1) Run the main component: +``` +cd ../../PoseBasedGestureRecognition +python src/PoseBasedGestureRecognition.py etc/config +``` + +2) Run the client: ``` -bin/PoseBasedGestureRecognitionClient config +cd ../test/poseBasedGestureRecognitionClient +python src/PoseBasedGestureRecognitionClient.py etc/config ```