libXCam相机功能扩展开发库

libXCam是一个扩展相机功能的项目，专注于图像质量改进和视频分析。 图像预处理，图像后处理和智能分析支持许多功能。 该库使GPU / CPU / ISP协同工作以提高图像质量。 OpenCL用于提高不同平台的性能。

主要特性：

• Image processing features
  
  
  
  • Advanced features
    
    
    
    • Automotive surround view(360) stitching (OpenCL/CPU/GLES)
      
      
      
      • Support bowl view 3D model stitching by 4 video input.
      
      
      • Enable geometry remap for WFoV camera calibration(intrinsic and extrinsic data).
      
      
      • Quality and performance improved (OpenCL/CPU/GLES).
      
      
      • CPU version upstreamed into AOSP for automotive surround view.
      
      
      • Enable Vulkan to improve performance.
      
      
    
    
    • 360 video stitching (Equirectangular mode via OpenCL)
      
      
      
      • Support 2-fisheye (>180 degree) video stream stitching.
      
      
      • Performance and quality improved.
      
      
    
    
    • DNN inference framework
      
      
      
      • Support pedestrian and vehicle detection.
      
      
    
    
    • Digital Video Stabilization
      
      
      
      • OpenCV feature-matched based video stabilization.
      
      
      • gyroscope 3-DoF (orientation) based video stabilization.
      
      
    
    
    • Blender: multi-band blender (OpenCL/CPU/GLES)
    
    
    • Noise reduction (OpenCL)
      
      
      
      • adaptive NR based on wavelet-haar and Bayersian shrinkage.
      
      
      • 3D-NR with inter-block and intra-block reference.
      
      
      • wavelet-hat NR (obsolete).
      
      
    
    
    • Wide dynamic range (WDR) (OpenCL)
      
      
      
      • histogram adjustment tone-mapping.
      
      
      • gaussian-based tone-mapping (obsolete).
      
      
    
    
    • Fog removal: retinex and dark channel prior algorithm (OpenCL)
      
      
      
      • dark channel prior algorithm based defog.
      
      
      • multi-scale retinex based defog (obsolete).
      
      
    
    
  
  
  • Basic pipeline from bayer to YUV/RGB format (OpenCL / AtomISP)
    
    
    
    • Gamma correction, MACC, color space, demosaicing, simple bilateral noise reduction, edge enhancement and temporal noise reduction.
    
    
  
  
  • 3A features
    
    
    
    • Auto whitebalance, auto exposure, auto focus, black level correction, color correction, 3a-statistics calculation.
    
    
  
  


• Support 3rd party 3A lib which can be loaded dynamically
  
  
  
  • hybrid 3a plugin.
  
  


• Support 3a analysis tuning framework for different features


• Support smart analysis framework
  
  
  
  • Face detection interface/plugin.
  
  


• Enable gstreamer plugin
  
  
  
  • xcamsrc, capture from usb/isp camera, process 3a/basic/advanced features.
  
  
  • xcamfilter, improve image quality by advanced features and smart analysis.
  
  

环境要求：

• install gcc/g++, automake, autoconf, libtool, gawk, pkg-config


• Linux kernel > 3.10


• install ocl-icd-dev, ocl-icd-opencl-dev


• If --enable-gst, need install libgstreamer1.0-dev, libgstreamer-plugins-base1.0-dev


• If --enable-aiq, need get ia_imaging lib which we don't support


• If --enable-libcl, need compile or install OpenCL driver


• If --enable-opencv, suggest OpenCV versions [3.0.0 - 3.4.3] (or: OpenCV Wiki)


• If --enable-render, need compile OpenSceneGraph library with configure option "-DOSG_WINDOWING_SYSTEM=X11"


• If --enable-gles, need to install Mesa3D library


• If --enable-vulkan, need to install Mesa3D library


• If --enable-dnn, need to compile OpenVino inference-engine