feat: 切换后端至PaddleOCR-NCNN，切换工程为CMake

1.项目后端整体迁移至PaddleOCR-NCNN算法，已通过基本的兼容性测试
2.工程改为使用CMake组织，后续为了更好地兼容第三方库，不再提供QMake工程
3.重整权利声明文件，重整代码工程，确保最小化侵权风险

Log: 切换后端至PaddleOCR-NCNN，切换工程为CMake
Change-Id: I4d5d2c5d37505a4a24b389b1a4c5d12f17bfa38c

3rdparty/opencv-4.5.4/modules/video/doc/video.bib

@@ -0,0 +1,44 @@
+@article{AAM,
+  title={Adaptive appearance modeling for video tracking: survey and evaluation},
+  author={Salti, Samuele and Cavallaro, Andrea and Di Stefano, Luigi},
+  journal={Image Processing, IEEE Transactions on},
+  volume={21},
+  number={10},
+  pages={4334--4348},
+  year={2012},
+  publisher={IEEE}
+}
+
+@article{AMVOT,
+  title={A survey of appearance models in visual object tracking},
+  author={Li, Xi and Hu, Weiming and Shen, Chunhua and Zhang, Zhongfei and Dick, Anthony and Hengel, Anton Van Den},
+  journal={ACM Transactions on Intelligent Systems and Technology (TIST)},
+  volume={4},
+  number={4},
+  pages={58},
+  year={2013},
+  publisher={ACM}
+}
+
+@inproceedings{GOTURN,
+  title={Learning to Track at 100 FPS with Deep Regression Networks},
+  author={Held, David and Thrun, Sebastian and Savarese, Silvio},
+  booktitle={European Conference Computer Vision (ECCV)},
+  year={2016}
+}
+
+@inproceedings{Kroeger2016,
+  author={Till Kroeger and Radu Timofte and Dengxin Dai and Luc Van Gool},
+  title={Fast Optical Flow using Dense Inverse Search},
+  booktitle={Proceedings of the European Conference on Computer Vision ({ECCV})},
+  year={2016}
+}
+
+@inproceedings{MIL,
+  title={Visual tracking with online multiple instance learning},
+  author={Babenko, Boris and Yang, Ming-Hsuan and Belongie, Serge},
+  booktitle={Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on},
+  pages={983--990},
+  year={2009},
+  organization={IEEE}
+}