Alternatives and similar repositories for AI-on-Board:

Users that are interested in AI-on-Board are comparing it to the libraries listed below

• ZhangLi1210 / NanoTrack_Tensorrt_Cpp
  NanoTrack(@HonglinChu), C++ TensorRT deployment. MAX 250 FPS!
  ☆23Updated last year
• cqu20160901 / yolov8-obb_onnx_rknn_horizon_tensonRT
  yolov8 旋转目标检测部署，瑞芯微RKNN芯片部署、地平线Horizon芯片部署、TensorRT部署
  ☆26Updated 9 months ago
• Qengineering / YoloV8-NPU
  YoloV8 NPU for the RK3566/68/88
  ☆49Updated 8 months ago
• aemior / yolov8n_rk3588
  ☆34Updated last year
• Try2ChangeX / NanoTrack_RK3588_python
  python版本基于rk3588的NanoTrack,每秒可达120FPS
  ☆103Updated 2 years ago
• Qengineering / YoloV10-NPU
  YoloV10 NPU for the RK3566/68/88
  ☆13Updated 8 months ago
• cqu20160901 / yolov8seg_rknn_Cplusplus
  yolov8seg 瑞芯微 rknn 板端 C++部署，使用平台 rk3588。
  ☆23Updated 10 months ago
• dog-qiuqiu / simple-rknn2
  The rknn2 API uses the secondary encapsulation of the process, which is easy for everyone to call. It is applicable to rk356x rk3588
  ☆45Updated 2 years ago
• LittleRain626 / rknn_yolov5_3588_bytetrack
  ☆23Updated 2 years ago
• zhuyuliang / LightTrack-rknn
  RKNN version demo of [CVPR21] LightTrack: Finding Lightweight Neural Network for Object Tracking via One-Shot Architecture Search
  ☆21Updated 3 years ago
• MontaukLaw / yolov5_3588_multi_thread
  启动多线程, relu激活, 3588的yolo部署, 帧率150以上.
  ☆18Updated last year
• autoexpect / rknn_ffmpeg_tutorial
  ffmpeg->rockchip mpp decoding->rknpu rknn->opencv opengl rendering
  ☆39Updated 2 years ago
• cqu20160901 / yolov10_rknn_Cplusplus
  yolov10 瑞芯微 rknn 板端 C++部署，使用平台 rk3588。
  ☆65Updated 7 months ago
• crab2rab / RKNN-YOLOV5-BatchInference-MultiThreading
  RKNN-YOLOV5-BatchInference-MultiThreadingYOLOV5多张图片多线程C++推理
  ☆18Updated last year
• rscgg37248 / DeepStream6.0_Yolov5-6.0
  基于DeepStream6.0和yolov5-6.0的目标检测
  ☆19Updated 3 years ago
• cluangar / YOLOv5-RK3588-Python
  Modify Code From rknn-toolkit2
  ☆46Updated 6 months ago
• cqu20160901 / yolov8pose_rknn_Cplusplus
  yolov8pose 瑞芯微 rknn 板端 C++部署。
  ☆34Updated last year
• Try2ChangeX / NanoTrack_Libtorch
  C++版本基于libtorch的NanoTrack跟踪算法
  ☆44Updated 2 years ago
• l-sf / Track-trt
  基于 TensorRT 的 C++ 高性能单目标跟踪推理，支持算法OSTrack、LightTrack。
  ☆46Updated last year
• cqu20160901 / yolov11_dfl_rknn_Cplusplus
  yolov11 瑞芯微 rknn 板端 C++部署，使用平台 rk3588。
  ☆40Updated this week
• crab2rab / MonocularDistanceDetect-YOLOV5-RKNN-CPP-MultiThread
  基于yolov5的C++单目摄像头测距
  ☆34Updated last year
• Try2ChangeX / sort_cpp
  C++版本的sort算法，可无缝添加在检测器后进行实时多目标跟踪
  ☆11Updated 2 years ago
• Qengineering / YoloV5-NPU
  YoloV5 NPU for the RK3566/68/88
  ☆94Updated 8 months ago
• cqu20160901 / FastSAM_onnx_rknn
  FastSAM 部署版本，便于移植不同平，部署简单、运行速度快。
  ☆18Updated 9 months ago
• wzxzhuxi / rknn-3588-npu-yolo-accelerate
  rknn-3588部署yolov5，利用线程池实现npu推理加速；Deploying YOLOv5 on RKNN-3588, utilizing a thread pool to achieve NPU inference acceleration.
  ☆57Updated 6 months ago
• delta1037 / RknnInferTemplate
  RKNN模型推理部署模板
  ☆21Updated last year
• EZreal-zhangxing / rk_ffmpeg
  在rockchip3588上实现用ffmpeg进行推拉流，其中推拉流使用硬件加速编解码
  ☆62Updated last year
• cqu20160901 / yolov11_tensorRT_postprocess_cuda
  yolov11 的tensorRT C++ 部署，后处理使用cuda实现比较耗时的操作。
  ☆30Updated 2 months ago