Contact Us
CiiS Lab
Johns Hopkins University
112 Hackerman Hall
3400 N. Charles Street
Baltimore, MD 21218
Directions

Lab Director
Russell Taylor
127 Hackerman Hall
rht@jhu.edu

Trace:

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
courses:456:2023:projects:456-2023-04:project-04 [2023/05/15 02:14] – [Project Management] ywang790courses:456:2023:projects:456-2023-04:project-04 [2023/05/15 02:47] (current) – [Vision Guided Mosquito Dissection for the Production of Malaria Vaccine] ywang790
Line 1: Line 1:
 ======Vision Guided Mosquito Dissection for the Production of Malaria Vaccine====== ======Vision Guided Mosquito Dissection for the Production of Malaria Vaccine======
-**Last updated: 05/10/2023, 7 p.m.**+**Last updated: 05/14/2023, 7 p.m.**
  
  
Line 22: Line 22:
 {{ :courses:456:2023:projects:456-2023-04:图片2.jpg?400 |}} {{ :courses:456:2023:projects:456-2023-04:图片2.jpg?400 |}}
  
-======Background, Specific Aims, and Significance======+======Background, Specific Aims/Goals, and Significance======
  
 ===== Background: ===== ===== Background: =====
Line 31: Line 31:
 However, the current extraction process is fully manual and requires highly trained technicians to perform delicate manual operations under a microscope. The process is time-consuming and expensive. An automated dissection process is being developed at LCSR that uses a robotic microsurgical instrument to manipulate mosquitoes. The autonomy of the robotic system hinges on sophisticated computer vision methods to detect mosquitoes and their body parts and to provide quality control during the process.  However, the current extraction process is fully manual and requires highly trained technicians to perform delicate manual operations under a microscope. The process is time-consuming and expensive. An automated dissection process is being developed at LCSR that uses a robotic microsurgical instrument to manipulate mosquitoes. The autonomy of the robotic system hinges on sophisticated computer vision methods to detect mosquitoes and their body parts and to provide quality control during the process. 
  
-===== Specific Aims: =====+===== Specific Aims/Goals: =====
  
  This project aims to create vision algorithms for the robot mosquito dissection system, which is an important part of continuing development. Specific aims are to develop new DL-based CV methods and integrate existing CV methods for the mosquito dissection system, which include:  This project aims to create vision algorithms for the robot mosquito dissection system, which is an important part of continuing development. Specific aims are to develop new DL-based CV methods and integrate existing CV methods for the mosquito dissection system, which include:
Line 58: Line 58:
 {{ :courses:456:2023:projects:456-2023-04:wechat_image_20230508175602.png?600 |}} {{ :courses:456:2023:projects:456-2023-04:wechat_image_20230508175602.png?600 |}}
  
-**Code in Gitlab repository for these tasks:** +======Project Outcomes and Technical Documentation====== 
 + 
 +**Codes and label files in Gitlab repository for these tasks: (Access to the project Gitlab is required. Ask Prof.Russell H. Taylor or Balazs Vagvolgyi to grant permission.)** 
  
 Classification Deep Learning Architectures: https://git.lcsr.jhu.edu/mosquito-vision/sanaria_cv_dl/-/tree/main/lib/sanaria_classification_dl Classification Deep Learning Architectures: https://git.lcsr.jhu.edu/mosquito-vision/sanaria_cv_dl/-/tree/main/lib/sanaria_classification_dl
Line 70: Line 72:
 Prediction of Dissection Success: https://git.lcsr.jhu.edu/mosquito-vision/sanaria_cv_dl/-/tree/main/tasks/success_prediction_2 Prediction of Dissection Success: https://git.lcsr.jhu.edu/mosquito-vision/sanaria_cv_dl/-/tree/main/tasks/success_prediction_2
  
-**GitLab Wiki for these tasks:**+**GitLab Wiki and documentation for these tasks: (Access to the project Gitlab is required. Ask Prof.Russell H. Taylor or Balazs Vagvolgyi to grant permission.)**
  
 Classification Deep Learning Architectures: https://git.lcsr.jhu.edu/mosquito-vision/sanaria_cv_dl/-/wikis/Classification-Deep-Learning-Architectures Classification Deep Learning Architectures: https://git.lcsr.jhu.edu/mosquito-vision/sanaria_cv_dl/-/wikis/Classification-Deep-Learning-Architectures
Line 87: Line 89:
 Here is a flow chart of the technical approach: Here is a flow chart of the technical approach:
  
-{{ :courses:456:2023:projects:456-2023-04:未命名文件_10_.png?200 |}}+{{ :courses:456:2023:projects:456-2023-04:流程图.png?400 |}}
  
 **Images and Annotations** **Images and Annotations**
Line 124: Line 126:
 {{ :courses:456:2023:projects:456-2023-04:fig1.png?600 |}} {{ :courses:456:2023:projects:456-2023-04:fig1.png?600 |}}
  
-======Project Management ====== +======Project Management Summary====== 
-  * **Yutai Wang (Team Leader/ Team Member):** Responsible for all tasks. Developed classification neural networks. Collected image data and collaborated with labeling. Designed the experiment platform and conducted experiments for the extra work. Wrote documentation and uploaded corresponding codes to project’s Gitlab for each task. +  * **Credits** 
-  * **Balazs Vagvolgyi (Mentor):** Provide mentorship. Have regular weekly meeting with me to discuss results and determine what should be the next step. +  - **Yutai Wang (Team Leader/ Team Member):** Responsible for all tasks. Developed classification neural networks. Collected image data and collaborated with labeling. Designed the experiment platform and conducted experiments for the extra work. Wrote documentation and uploaded corresponding codes to project’s Gitlab for each task. 
 +  - **Balazs Vagvolgyi (Mentor):** Provide mentorship. Have regular weekly meeting with me to discuss results and determine what should be the next step. 
 +  * **Accomplished VS Planned** 
 +{{ :courses:456:2023:projects:456-2023-04:wechat_image_20230514223407.png?600 |}} 
 +  * **Future Plan** 
 +  - Based on the Prediction of Dissection Success results, investigate methods to locate specific regions on mosquito images that contribute strongest to variability in exudate quality. Record relevant codes and documentation in Gitlab. 
 +  - Develop exudate volume estimation based on deep learning methods. Complete exudate volume estimation codes in Gitlab repository. Write documentation in Gitlab Wiki and Readme files.
  
 ======Reports and presentations====== ======Reports and presentations======
courses/456/2023/projects/456-2023-04/project-04.1684116855.txt.gz · Last modified: by ywang790




ERC CISST    LCSR    WSE    JHU