|
|
Visual detection of small objects using available tools in MATLAB
Sladký, Jiří ; Dobossy, Barnabás (referee) ; Appel, Martin (advisor)
This thesis investigates possibilities of small object detection in pictures using YOLO method, a deep learning algorithm available in MATLAB. In the thesis, a detector was designed and trained to detect cows from top-down view. A tool was created, that performs detection using the proposed model even on high resolution images and counts the present objects. A generator of synthetic images was programmed, which helped with training the model. Various experiments were performed that found the limits of YOLO and validated contribution of the proposed improvements.
|
|
|
Detection and classification of objects of interest for watering mobile robot using image processing
Sladký, Jiří ; Šnajder, Jan (referee) ; Krejsa, Jiří (advisor)
This thesis deals with image processing on autonomous watering mobile robot using embedded computer NVIDIA Jetson Nano. A method for object detection, YOLOv5, was chosen, which served for detection of flowers and flower pots. Using a method for monocular depth estimation, MiDaS, relative depth map was predicted. An algorithm was created, which converted this map to metric depth map using data from LiDAR. Thanks to that, distance of the detected flowers could be estimated. The created tools were implemented in ROS framework and tested on real data form indoor environment.
|
|
|
Detection and classification of objects of interest for watering mobile robot using image processing
Sladký, Jiří ; Šnajder, Jan (referee) ; Krejsa, Jiří (advisor)
This thesis deals with image processing on autonomous watering mobile robot using embedded computer NVIDIA Jetson Nano. A method for object detection, YOLOv5, was chosen, which served for detection of flowers and flower pots. Using a method for monocular depth estimation, MiDaS, relative depth map was predicted. An algorithm was created, which converted this map to metric depth map using data from LiDAR. Thanks to that, distance of the detected flowers could be estimated. The created tools were implemented in ROS framework and tested on real data form indoor environment.
|
|
|
Visual detection of small objects using available tools in MATLAB
Sladký, Jiří ; Dobossy, Barnabás (referee) ; Appel, Martin (advisor)
This thesis investigates possibilities of small object detection in pictures using YOLO method, a deep learning algorithm available in MATLAB. In the thesis, a detector was designed and trained to detect cows from top-down view. A tool was created, that performs detection using the proposed model even on high resolution images and counts the present objects. A generator of synthetic images was programmed, which helped with training the model. Various experiments were performed that found the limits of YOLO and validated contribution of the proposed improvements.
|
|
| |
guest ::
RSS feed.