JeVoisBase  1.3
JeVois Smart Embedded Machine Vision Toolkit Base Modules
Share this page:
JeVoisBase component algorithms
Collaboration diagram for JeVoisBase component algorithms:

Modules

 Image filters
 

Classes

class  ArUco
 Simple wrapper class over the opencv_contrib ArUco augmented reality markers. More...
 
class  EyeTracker
 Eye-tracker class used to detect gaze direction from close-up video of one's eye. More...
 
class  FaceDetector
 Face detection using OpenCV. More...
 
class  FilterGPU
 Simple image filtering using OpenGL-ES on the GPU. More...
 
class  SuperPixel
 Superpixel image segmentation from OpenCV. More...
 
class  ObjectMatcher
 Object matching using OpenCV keypoint detection and matching. More...
 
struct  ObjectMatcher::TrainData
 Training data structure for ObjectMatcher. More...
 
class  ObjectRecognitionBase
 Abstract base class for an object recognition component. More...
 
class  ObjectRecognition< NetType >
 Wrapper around a neural network implemented by with the tiny-dnn framework by Taiga Nomi. More...
 
class  ObjectRecognitionCIFAR
 Object recognition CNN for CIFAR-10 dataset. More...
 
class  ObjectRecognitionILAB
 Object recognition CNN for ILAB-10 dataset. More...
 
class  ObjectRecognitionMNIST
 Object recognition CNN for MNIST handwritten digits. More...
 
class  FastOpticalFlow
 Fast optical flow computation using dense inverse search. More...
 
class  QRcode
 QRcode and Barcode detection using ZBar. More...
 
class  RoadFinder
 Navigation by finding road. More...
 
class  Saliency
 Simple wrapper class around Rob Peter's C-optimized, fixed-point-math visual saliency code. More...
 
struct  Saliency::visitor_data
 
class  Surprise
 Compute Itti & Baldi surprise over video frames. More...
 
class  Kalman2D
 Simple component to track a moving 2D point over time using a Kalman filter. More...
 
class  BufferedVideoReader
 Simple class to read video frames from a movie file, decode them, and buffer them for smooth playback. More...
 

Detailed Description

JeVois provides the ability to implement individual machine vision algorithms as Component objects, which combine the implementation of the algorithm itself, and of parameters that are exposed to users to tune the algorithm's operation.

Component algorithms can be shared and assembled into hierarchies to give rise to different machine vision modules.