Improve documentation by adding tutorials

[yuyu2172]

Some ideas on possible tutorials to add:

• [x] Object Detection Tutorial
  • bbox in ChainerCV
  • BboxDataset
  • Object Detection Link interface
  • Evaluating performance of Object Detection Link
  • Training object detection (I am only planning to add links to examples)
• [ ] Semantic Segmentation tutorial
• [ ] Feature extraction model and classification tutorial
• [ ] Transforms and TransformDataset tutorial

I am also thinking of simplifying the README a lot. https://github.com/yuyu2172/chainercv/tree/readme