- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I am running crossroad_camera_demo,
According to its readme, there are two main detection networks responsible for detecting people:
person-vehicle-bike-detection-crossroad-0078
person-vehicle-bike-detection-crossroad-1016
When I use 0078 as the main detection network, if a person is detected, it will be framed on the image;
But when I use 1016 as the main detection network, no object will be framed
And I added the -r parameter to display the inference results, according to the inference results, people are detected.
How should I solve this problem?
Any help would be greatly appreciated, thank you!
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi STATEABC,
For your information, the default value for parameter -person_label is 1, which is for the person-vehicle-bike-detection-crossroad-0078 model.
Hence, for the demo to work correctly, the command line parameter -person_label 2 should be added for the person-vehicle-bike-detection-crossroad-1016 model.
Regards,
Peh
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi STATEABC,
For your information, the default value for parameter -person_label is 1, which is for the person-vehicle-bike-detection-crossroad-0078 model.
Hence, for the demo to work correctly, the command line parameter -person_label 2 should be added for the person-vehicle-bike-detection-crossroad-1016 model.
Regards,
Peh
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi STATEABC,
This thread will no longer be monitored since this issue has been resolved. If you need any additional information from Intel, please submit a new question.
Regards,
Peh

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page