Abstract | ||
---|---|---|
We propose novel representations for functions of an object, namely Task-oriented Function, which is improved upon the idea of Afforadance in the field of Robotics Vision. We also propose a convolutional neural network to detect task-oriented functions. This network takes as input an operational task as well as an RGB image and assign each pixel an appropriate label for every task. Task-oriented funciton makes it possible to descibe various ways to use an object because the outputs from the network differ depending on operational tasks. We introduce a new dataset for task-oriented function detection, which contains about 1200 RGB images and 6000 pixel-level annotations assuming five tasks. Our proposed method reached 0.80 mean IOU in our dataset. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ICAR46387.2019.8981633 | 2019 19th International Conference on Advanced Robotics (ICAR) |
Keywords | Field | DocType |
task-oriented function detection,operational task,convolutional neural network,RGB image,robotics vision,pixel-level annotations | Astronomy,Computer vision,Convolutional neural network,Rgb image,RGB color model,Artificial intelligence,Pixel,Task oriented,Robotics,Physics | Conference |
ISBN | Citations | PageRank |
978-1-7281-2468-1 | 0 | 0.34 |
References | Authors | |
2 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuchi Ishikawa | 1 | 0 | 1.35 |
Haruya Ishikawa | 2 | 0 | 0.34 |
Shuichi Akizuki | 3 | 0 | 0.34 |
Masaki Yamazaki | 4 | 0 | 0.34 |
Yasuhiro Taniguchi | 5 | 3 | 1.84 |
Yoshimitsu Aoki | 6 | 80 | 23.65 |