Project
| # | Title | Team Members | TA | Documents | Sponsor |
|---|---|---|---|---|---|
| 12 | Laser System to Shoot Down Mosquitos |
Fan Yang Ruochen Wu Yuxin Qu Zhongqi Wu |
Xinyi Xu | design_document1.pdf final_paper1.pdf other8.pdf proposal1.pdf |
Timothy Lee |
| # Laser System to Shoot Down Mosquitos ## Team Member - Ruochen Wu (rw12) - Yuxin Qu (yuxin19) - Zhongqi Wu (zhongqi19) - Fan Yang (fy10) ## Problem In the world, there are thousands of humans suffering from the disease and death brought by bite from mosquito. Therefore, an effective method of protection against mosquitoes is necessary. Tracking the mosquito and using a laser to kill it may be a feasible solution. ## Solution Overview Firstly, the laser gun attached to the camera will emit a low-power laser to illustrate the drop point. To position the mosquito, we employ the yolov5s on our computation platform to do real-time detection. We move the camera to diminish the distance between the drop point and the mosquito until they coincide. The laser gun then emits a high-power laser to destroy the mosquito. But there are many challenges in implementation. The first one is the computing platform. The embedded development board may be incapable to run yolov5. We are considering those with NPU or CUDA support. Cloud Computing is another solution. But it possibly has high latency and low stability. Besides, the mosquito is very tiny and possibly occupies only a few pixels on the frame. If necessary, we may use radar to help with the detection. Also, the security of the laser is a major problem. We plan to do the safety check before emitting it and find a proper power that is harmless to humans. ## Solution Components: #### 1. Positioning system: - High resolution camara - Low power laser for aiming - Software employing yolov5 - Computing platform (cloud server or embedded development board) #### 2. Attacking system: - Driver control module - Rotation motor - High power laser for shooting ## Criterion for Success 1. Be able to detect a mosquito in the scene from a camera and locate its position. 2. The lasing device can target and shoot the mosquito. 3. The laser does not harm people. ## Distribution of Work Ruochen and Zhongqi are responsible for the training of yolov5 on mosquito datasets. Though the mosquito is very small and the procesing speed is limited by the device, they are both ECE students and have got lots of experience in deep learning. Fan will handle the deployment of yolov5 on embedded device, who is majoring in ECE. It takes time to get familiar with the environment of the board and make full use of the computing resource. Yuxin will take charge of the driver control module, laser and motors. Yuxin is EE student, who is familiar with the control system. Though we all lack mechanical experience, it accounts for a little portion of the project. |
|||||