Lab 3 4 - PoojaShekhar/CS5543-Real-Time-Big-Data-Analytics--Lab-assignments GitHub Wiki

Questions

Implement a video application using shot transition (called the key frame detection) technique covered in Tutorial 3 for an interesting use-case related to your project. Construct a short video using key frames. Also, generate the metadata (such as video length, number of frames, main frames).

Total 346 frames were there in the video.Out of which 53 frames were collected.And a shorter video was made.

Implement a video application similar to Video Processing Demo and Video SIFT covered in Tutorial 4 for an interesting use-case related to your project. Use your own Model for Object Detection (File) and annotate the frames (for any given video or webcam) with bounding box and text which ever matches the object model. Implementation is completely on OpemImaj.

These tags were generated while the video was running.

[Tag transportation system: 0.9575752019882202] [Tag car: 0.9702942371368408] [Tag transportation system: 0.9795825481414795] [Tag transportation system: 0.984687864780426] [Tag transportation system: 0.984242856502533] [Tag travel: 0.9537791013717651] [Tag car: 0.9738723635673523] [Tag transportation system: 0.9816247224807739] [Tag transportation system: 0.984207272529602] [Tag people: 0.9881836175918579]

A sample tagged frame is provided below.