PyDetectionDNN.PyDetectionDNN Class Reference

Object detection and recognition using OpenCV Deep Neural Networks (DNN) More...

Public Member Functions
def	__init__ (self)
	Constructor. More...
def	postprocess (self, frame, outs)
	Analyze and draw boxes, object names, and confidence scores. More...
def	process (self, inframe, outframe)
	JeVois main processing function. More...

Public Attributes
	confThreshold
	nmsThreshold
	inpWidth
	inpHeight
	scale
	mean
	rgb
	classes
	net
	timer
	model
	outNames

Detailed Description

Object detection and recognition using OpenCV Deep Neural Networks (DNN)

This module runs an object detection deep neural network using the OpenCV DNN library. Detection networks analyze a whole scene and produce a number of bounding boxes around detected objects, together with identity labels and confidence scores for each detected box.

This module supports detection networks implemented in TensorFlow, Caffe, Darknet, Torch, etc as supported by the OpenCV DNN module.

Included with the standard JeVois distribution are:

• OpenCV Face Detector, Caffe model
• MobileNet + SSD trained on Pascal VOC (20 object classes), Caffe model
• MobileNet + SSD trained on Coco (80 object classes), TensorFlow model
• MobileNet v2 + SSD trained on Coco (80 object classes), TensorFlow model
• Darknet Tiny YOLO v3 trained on Coco (80 object classes), Darknet model
• Darknet Tiny YOLO v2 trained on Pascal VOC (20 object classes), Darknet model

See the module's constructor (init) code and select a value for model to switch network. Object categories are as follows:

• The 80 COCO object categories are: person, bicycle, car, motorbike, aeroplane, bus, train, truck, boat, traffic, fire, stop, parking, bench, bird, cat, dog, horse, sheep, cow, elephant, bear, zebra, giraffe, backpack, umbrella, handbag, tie, suitcase, frisbee, skis, snowboard, sports, kite, baseball, baseball, skateboard, surfboard, tennis, bottle, wine, cup, fork, knife, spoon, bowl, banana, apple, sandwich, orange, broccoli, carrot, hot, pizza, donut, cake, chair, sofa, pottedplant, bed, diningtable, toilet, tvmonitor, laptop, mouse, remote, keyboard, cell, microwave, oven, toaster, sink, refrigerator, book, clock, vase, scissors, teddy, hair, toothbrush.
• The 20 Pascal-VOC object categories are: aeroplane, bicycle, bird, boat, bottle, bus, car, cat, chair, cow, diningtable, dog, horse, motorbike, person, pottedplant, sheep, sofa, train, tvmonitor.

Sometimes it will make mistakes! The performance of yolov3-tiny is about 33.1% correct (mean average precision) on the COCO test set. The OpenCV Face Detector is quite fast and robust!

This module is adapted from the sample OpenCV code: https://github.com/opencv/opencv/blob/master/samples/dnn/object_detection.py

More pre-trained models are available on github in opencv_extra

Author

Laurent Itti

Videomapping:

YUYV 640 502 20.0 YUYV 640 480 20.0 JeVois PyDetectionDNN

Email:

itti@.nosp@m.usc..nosp@m.edu

Address:

880 W 1st St Suite 807, Los Angeles CA 90012, USA

Copyright

Copyright (C) 2018 by Laurent Itti

Main URL:

http://jevois.org

Support URL:

http://jevois.org

Other URL:

http://jevois.org

License:

GPL v3

Distribution:

Unrestricted

Restrictions:

None

Definition at line 61 of file PyDetectionDNN.py.

Constructor & Destructor Documentation

__init__()

def PyDetectionDNN.PyDetectionDNN.__init__

(

self

)

Constructor.

Definition at line 64 of file PyDetectionDNN.py.

Member Function Documentation

postprocess()

def PyDetectionDNN.PyDetectionDNN.postprocess	(		self,
			frame,
			outs
	)

Analyze and draw boxes, object names, and confidence scores.

Definition at line 134 of file PyDetectionDNN.py.

References PyPostClassify.PyPostClassify.classes, PyPostDAMOyolo.PyPostDAMOyolo.classes, PyPostYolo.PyPostYolo.classes, PyClassificationDNN.PyClassificationDNN.classes, PyDetectionDNN.PyDetectionDNN.classes, Darknet.classes, Yolo.classes, PyClassificationDNN.PyClassificationDNN.confThreshold, PyDetectionDNN.PyDetectionDNN.confThreshold, demo.float, demo.int, PyNetOpenCV.PyNetOpenCV.net, PyClassificationDNN.PyClassificationDNN.net, PyDetectionDNN.PyDetectionDNN.net, Darknet.net, Yolo.net, ObjectRecognition< NetType >.net, PyDetectionDNN.PyDetectionDNN.nmsThreshold, and PyDetectionDNN.PyDetectionDNN.outNames.

Referenced by PyDetectionDNN.PyDetectionDNN.process().

process()

def PyDetectionDNN.PyDetectionDNN.process	(		self,
			inframe,
			outframe
	)

JeVois main processing function.

Definition at line 252 of file PyDetectionDNN.py.

References PyClassificationDNN.PyClassificationDNN.inpHeight, PyDetectionDNN.PyDetectionDNN.inpHeight, PyClassificationDNN.PyClassificationDNN.inpWidth, PyDetectionDNN.PyDetectionDNN.inpWidth, mobilenet_v1.MobileNetV1.mean, mobilenet_v2.MobileNetV2.mean, quantize-inc.Dataset.mean, transform.Normalize.mean, PyPreBlob.PyPreBlob.mean, PyClassificationDNN.PyClassificationDNN.mean, PyDetectionDNN.PyDetectionDNN.mean, mobilenet_v1.MobileNetV1.model, mobilenet_v2.MobileNetV2.model, mp_palmdet.MPPalmDet.model, lpd_yunet.LPD_YuNet.model, PyNetORT.PyNetORT.model, PyNetURetinex.PyNetURetinex.model, PyCoralDetect.PyCoralDetect.model, PyCoralSegment.PyCoralSegment.model, PyNetOpenCV.PyNetOpenCV.model, PyCoralClassify.PyCoralClassify.model, PyClassificationDNN.PyClassificationDNN.model, TensorFlow.model, PyDetectionDNN.PyDetectionDNN.model, PyNetOpenCV.PyNetOpenCV.net, PyClassificationDNN.PyClassificationDNN.net, PyDetectionDNN.PyDetectionDNN.net, Darknet.net, Yolo.net, ObjectRecognition< NetType >.net, PyDetectionDNN.PyDetectionDNN.outNames, PyPostDAMOyolo.PyPostDAMOyolo.postprocess(), PyDetectionDNN.PyDetectionDNN.postprocess(), DetectionDNN.postprocess(), PyCoralSegment.PyCoralSegment.rgb, PyCoralDetect.PyCoralDetect.rgb, PyClassificationDNN.PyClassificationDNN.rgb, PyCoralClassify.PyCoralClassify.rgb, PyDetectionDNN.PyDetectionDNN.rgb, PyPreBlob.PyPreBlob.scale, PyClassificationDNN.PyClassificationDNN.scale, PyDetectionDNN.PyDetectionDNN.scale, PyModule::__MODULE__.timer, PythonTutorial2::PythonTutorial2.timer, PyCoralDetect.PyCoralDetect.timer, PyCoralSegment.PyCoralSegment.timer, PyCoralClassify.PyCoralClassify.timer, PyClassificationDNN.PyClassificationDNN.timer, FirstPython.FirstPython.timer, and PyDetectionDNN.PyDetectionDNN.timer.

Member Data Documentation

classes

PyDetectionDNN.PyDetectionDNN.classes

Definition at line 84 of file PyDetectionDNN.py.

Referenced by PyDetectionDNN.PyDetectionDNN.postprocess().

confThreshold

PyDetectionDNN.PyDetectionDNN.confThreshold

Definition at line 65 of file PyDetectionDNN.py.

Referenced by PyDetectionDNN.PyDetectionDNN.postprocess().

inpHeight

PyDetectionDNN.PyDetectionDNN.inpHeight

Definition at line 68 of file PyDetectionDNN.py.

Referenced by PyDetectionDNN.PyDetectionDNN.process().

inpWidth

PyDetectionDNN.PyDetectionDNN.inpWidth

Definition at line 67 of file PyDetectionDNN.py.

Referenced by PyDetectionDNN.PyDetectionDNN.process().

mean

PyDetectionDNN.PyDetectionDNN.mean

Definition at line 70 of file PyDetectionDNN.py.

Referenced by PyDetectionDNN.PyDetectionDNN.process().

model

PyDetectionDNN.PyDetectionDNN.model

Definition at line 129 of file PyDetectionDNN.py.

Referenced by PyDetectionDNN.PyDetectionDNN.process(), and PyLicensePlate.PyLicensePlate.processGUI().

net

PyDetectionDNN.PyDetectionDNN.net

Definition at line 125 of file PyDetectionDNN.py.

Referenced by PyDetectionDNN.PyDetectionDNN.postprocess(), and PyDetectionDNN.PyDetectionDNN.process().

nmsThreshold

PyDetectionDNN.PyDetectionDNN.nmsThreshold

Definition at line 66 of file PyDetectionDNN.py.

Referenced by PyDetectionDNN.PyDetectionDNN.postprocess().

outNames

PyDetectionDNN.PyDetectionDNN.outNames

Definition at line 130 of file PyDetectionDNN.py.

Referenced by PyDetectionDNN.PyDetectionDNN.postprocess(), and PyDetectionDNN.PyDetectionDNN.process().

rgb

PyDetectionDNN.PyDetectionDNN.rgb

Definition at line 71 of file PyDetectionDNN.py.

Referenced by PyDetectionDNN.PyDetectionDNN.process().

scale

PyDetectionDNN.PyDetectionDNN.scale

Definition at line 69 of file PyDetectionDNN.py.

Referenced by PyDetectionDNN.PyDetectionDNN.process().

timer

PyDetectionDNN.PyDetectionDNN.timer

Definition at line 128 of file PyDetectionDNN.py.

Referenced by PyDMTX.PyDMTX.process(), PythonOpenCV.PythonOpenCV.process(), PythonSandbox.PythonSandbox.process(), PythonParallel.PythonParallel.process(), PyDetectionDNN.PyDetectionDNN.process(), PythonObject6D.PythonObject6D.process(), PyHandDetector.PyHandDetector.processGUI(), PyFaceMesh.PyFaceMesh.processGUI(), PyPoseDetector.PyPoseDetector.processGUI(), PySelfie.PySelfie.processGUI(), PyObjectron.PyObjectron.processGUI(), PyLicensePlate.PyLicensePlate.processGUI(), PySceneText.PySceneText.processGUI(), PythonTest.PythonTest.processGUI(), PythonSandbox.PythonSandbox.processGUI(), PythonSandbox.PythonSandbox.processNoUSB(), and PythonObject6D.PythonObject6D.processNoUSB().

---

The documentation for this class was generated from the following file:

• src/Modules/PyDetectionDNN/PyDetectionDNN.py