dlstreamer
GstKalman
dlstreamer | GstKalman | |
---|---|---|
2 | 1 | |
500 | 3 | |
2.4% | - | |
4.3 | 10.0 | |
12 days ago | over 1 year ago | |
C++ | C++ | |
MIT License | The Unlicense |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
dlstreamer
-
What is the best model and approach to identify a car model? Is a YOLO a good choice for that or is it better to user YOLO or RCNN or darknet for object detection and then use somethin like resnet152 to predict the exact model?
If you want object detection, classification (car models in your case) as well as tracking them, before getting your feet wet on model selection viz., Yolo, RCNN etc, check out Intel DLStreamer which uses GStreamer as the back end.... It uses Intel OpenVINO for inferencing and custom plugins for detection/classification and tracking also.... Intel has a big model zoo of pre-trained models, which can do the task of identifying the car models..... https://github.com/dlstreamer/dlstreamer
-
How would you approach hosting real time detection model in server/cloud?
https://github.com/dlstreamer/dlstreamer based on gstreamer
GstKalman
-
C++20 is great for wrapping C libraries
The unique_resource scope guard from the scope library generalizes well, for non-pointer type handles, example with gstreamer.
What are some alternatives?
vokoscreenNG - vokoscreenNG is a powerful screencast creator in many languages to record the screen, an area or a window (Linux only). Recording of audio from multiple sources is supported. With the built-in camera support, you can make your video more personal. Other tools such as systray, magnifying glass, countdown, timer, Showclick and Halo support will help
ncnn - ncnn is a high-performance neural network inference framework optimized for the mobile platform
AACS - Android Auto Server encapsulates communication with modern car infotainment system
TNN - TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.
nulloy - Music player with a waveform progress bar
openvino - OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference