When chatting with an old colleague a few days ago, I felt that it was helpful to activate a blog and record my technological growth process: Not only can I view my growth experience in the future, it can also be used as a form of supervision to remind you, the most important thing is that you can use a blog to have extensive and in-depth exchanges with experts, which is also a help for growth.
At present, my technological development goals are to focus on these areas: Video-based behavior recognition, video-based traffic violation/accident detection, and content-based image/video search.
Although there are many differences in these directions, there are still some similarities after all, and we hope to be able to communicate with each other.
Currently, the technical accumulation line can be as follows:
1. Image Feature Extraction: Master common and effective image processing technologies and follow up on the latest developments
2. Multiple Target Tracking: Moving Target Extraction + single pattern recognition should be able to form their own ideas
3. action sequence recognition: sequence pattern recognition is similar to HMM but should be different from hmm.
Because of the large data volume and high real-time requirementsAlgorithmIt is as simple, fast, effective, and robust as possible.