-
Hello,
I want to track pedestrians using Rekall. So i am taking detections per-frame and comparing the iou of detections in the previous frame. I am using join to merge and update the intervals whi…
-
## Implement/Get an model for object detection (even better if it can do instance seg like MaskRCNN)
We need it to include at least classes `['vehicle', 'pedestrian', 'sign', 'bicycle']`, everything …
-
Hello, author, when reproducing the code, I got the following results with regard to the evaluation indicators in simple, medium, and difficult cases. Why does the detection result on pedestrians appe…
-
Hi! Could you please tell me how can I use ByteTrack or QDTrack to implement multi-classes MOT? It seems that the existing configurations are only for one-class(pedestrian).
I wonder if my customized…
-
Thanks for sharing your work.
scrfd_person_2.5g.onnx model for [person detection](https://github.com/deepinsight/insightface/tree/master/examples/person_detection) is in not provided. please share it…
-
Dear Xiao Wang,
Thank you very much for your exciting work (NightSurveillance), which provides valuable data for the study of pedestrian detection at night. I have a question about whether you have…
-
Hi,
testing your evaluation with the provided ground truth `once_infos_val.pkl` as prediction does not yield the expected 100% mAP.
On some random two frames I obtain this:
```
|AP@50 |over…
-
Thanks for your implementation for vehicle detection and tracking by YOLO&DeepSort. I had a question that why you still use the pre-trained weight on MARS dataset (pedestrian dataset) to compare appea…
-
Is it possible to build dlib-android library in armeabi? I tried to by adding armeabi in Application.mk, but I am getting an error in build process. Here is the error:
```
[armeabi] Compile++ thu…
-
# Objective: Lane Detection for our CC20 Car
The lane Detection is an important task in autonomous driving.
# Goal
- Stable and fast line detection for trajectory generation
- detect the current…