update gitignore -> exclude hardware dox and old big dox, but keep todo and scrap/misc notes

.gitignore

 *.sublime-workspace
+a/hardware
+dox/old

a/setup/fov.py

+#!/usr/bin/python3
+
+# more background:
+# https://photographylife.com/sensor-crop-factors-and-equivalence
+
+from pprint import pprint as pp
+from math import *
+
+sensor_size_to_crop_factor={
+#can also calculate it manually by using diagonal sensor size and compare to full frame diagonal sensor size
+#https://shuttermuse.com/calculate-cameras-crop-factor/#digital-sensor-sizes-and-their-crop-factor
+"full frame":1, #reference: 36mm x 24mm -> diag:43.27
+"APS-C (Nikon etc.)":1.5,
+"APS-C (Canon)":1.6,
+'micro four thirds"':2,
+'1"':2.7,
+'2/3"':5.5,
+'1/1.8"':4.8,
+'1/2.3"':5.6,
+'1/2.5"':6,
+}
+
+focal_len_2_AOV_full_frame={
+11:117.1,
+14:104.3,
+16:96.7,
+24:73.7,
+35:54.4,
+50:39.6,
+85:23.9,
+100:20.4,
+150:13.7,
+}
+
+#equivalent_focal_length = focal_length_full_frame * crop_factor
+#fov - field of view (= horizontal angle of view)
+#size_subject
+#distance of subject
+
+def calc_fov(sensor_width_mm,f):
+	# for sensor_size, crop_factor in sensor_size_to_crop_factor:
+		# todo
+	# sensor_size='2/3"'
+	# crop_factor=sensor_size_to_crop_factor[sensor_size]
+	# pp(sensor_size)
+	# pp(crop_factor)
+
+	fov=2*atan(sensor_width_mm/(2*f)) * 180/pi #convert to degrees with 180/pi, same as degrees(...)
+	fov=round(fov,2)
+	return fov
+
+
+
+def calc_distance_to_subject(size_subject_cm, fov):
+	'''calc distance_to_subject from size_subject and fov using trigonometrics'''
+	'''depending on lense, the distance_to_subject is fixed or a minimum distance from the img plane'''
+
+	# distance_to_subject = (size_subject/2) / tan(radians(fov))
+	# distance_to_subject = round(distance_to_subject,2)
+
+	return distance_to_subject
+
+def main():
+	size_subject_cm=50
+	sensor_width_mm=36
+	f=11
+	fov=calc_fov(sensor_width_mm,f)
+	pp(f"fov: {fov}")
+
+	d=calc_distance_to_subject(size_subject_cm,fov)
+	pp(f"distance_to_subject: {d}")
+
+
+
+if __name__ == '__main__':
+	main()
+
+
+# formulae:
+# AOV (in degrees) = 2 ArcTan( sensor width / (2 X focal length)) * (180/π)
+# size_subject = 2 * (Tan (AOV/2) X Distance_to_Subject)
+

dox/install

+## software B - calc centroids
+################################
+g++ -ggdb  -o  `pkg-config --cflags --libs opencv4`
+
+
+camera_matrix 5678
+distortion_coefficients 76745
+
+where is the data?
+PATHIN="/data/ibtrack/move/input/rec$IDSTRING/"
+
+files:
+randlist.yml
+fileErrorList.yml
+
+
+## software A - grab pictures from camera
+#########################################
+Vimba Viewer:
+	see png to understand components architecture.
+	test: $INSTALL_DIR/Tools/Viewer/Bin/x86_64bit/VimbaViewer
+
+

dox/misc

+
+## industry cameras
+###############################
+5gige and 10gige more expensive + might get bandwidthproblems with 6cams? + 10gige need externalframegrabber
+usb2 - too old
+
+> usb3
+    - 4.5m cable
+    + usb3 interface card with 4 cams connected
+> gige
+    + 100m cable
+    hi res (20MP) and low fps, or
+    low res (2MP) and high fps
+    bandwith average. between usb2 and 3
+    -> can i reduce the fps manually?
+
+multiple cams:
+    star-network using an ethernet switch (bandwidth will be divided), or
+    a point-to-point network using an interface card with multiple GigE inputs.
+
+what interface gige card to use?
+    > needs to support PoE
+    > ETH from PC provides PoE? if no, then interface card
+
+## Heating:
+> cable:
+    cat6a is better than cat6 or 5e
+    dont bundle multiple cables together
+
+## lens
+420nm and 720nm and 800nm-1300nm IR
+IR corrected -> can be used for N IR
+
+problem: spheric abberation = rays farther from center are refracted to different focal point
+    > most @ max aperture (f1.8)
+problem: chromatic aberration = different colors (wavelentgths) have different focal lengths (sa. ~prisma)
+    > color finging
+    > longitudinal and lateral CA
+
+solutions:
+    > achromate = multi-lenses (doublet, triplet).
+        color correction (blue+red)
+    > aspheric
+        different form of lense (not spheric :)
+    > aspheric achromate
+        susceptible to scratch.
+        good quality
+-> ir-corrected doublet/triplet
+
+"fast aperture" = max aperture -> eg f1.8 needs to be quick to close all the way
+DOF
+-> is it possible to use a non-IR gigE cam with a IR-corrected lense, for nightvision?
+-> angle + distance
+    fixed or zoom lens
+
+-> cant get color img _and_ IR img at the same time
+    -> opt for IR, because it works with light and without
+
+thermal >= nightvision
+see through fog/grass?  ---
+
+
+450 2mp cam
+600 5mp cam
+
+Lense:
+calculate fixed focal length (fest brennweite)
+8mm >>
+6mm >> 225oi
+5mm >> 60cm
+
+<900nm QE           ringlichter >> NIR.
+
+calculation:
+> 50 cm diameter -> 500mm
+> 2.4 MP (1936x1216) -> 1216 pix per line
+1216 / 500 = 2.4 px/mm
+small insect = 4mm -> 8px -> 8*8 = 64px...
+
+
+-> can i use SWIR for VS as well? yes, but they are unaffordably expensive
+-> SWIR for RaspPi? or usb3? cheaper?
+
+## DOF - Schärfentiefe - Tiefenschärfe
+#############################################################
+https://photographylife.com/what-is-depth-of-field
+app: simple DOF calculator
+https://www.edmundoptics.com/c/achromatic-lenses/652/#
+
+> more DOF on
+    * smaller focal length
+    * lower aperture eg f16 > landscape
+
+> less DOF
+    * high aperture eg f1.8
+    * larger focal length -> zoom 150mm
+    > BOKEH. nice creamy background
+    > macro, landscape with FG-POI
+
+> f5.6 sharpest + best middle ground
+
+## crop factor // sensorsize
+    > equivalent focal length
+        eg. olympus 2x
+        8mm > 16mm - narrower
+        100mm > 200mm -more zoom (fake crop zoom)
+
+    > calc equiv. focal length:
+        https://www.translatorscafe.com/unit-converter/en-US/calculator/lens-efl/
+
+    > smaller sensor
+        = more crop and more "zoom" (narrower field of view, less DOF)
+        = less light, dynamic range, pixelsize
+        = less pixels (normally)
+
+    > bigger sensor
+        = less crop, wider field of view -> can crop manually (but more DOF)
+
+##build myself... IoT / embedded camera
+  raspberryPi + CAM
+    > 15€ possible?
+    > https://www.raspberrypi.com/products/raspberry-pi-zero-2-w/
+  MIPI CSI2 - interface -> all Pis have interface
+  >> datarates?
+  >> IR / lowlight compatible?
+  >> howto make rugged?
+
+  nvidia jetson nano?
+  https://www.nvidia.com/de-de/autonomous-machines/embedded-systems/jetson-nano/
+
+csi(2) - pi: camera serial interface
+dsi(2) - pi: display serial interface
+csi/dsi -> max len 25cm!
+    --> via FPD-Link III up to 15m
+    --> GSML2 ?
+###############################
+hub/repeater > just cp data to all connected
+switch       >
+router       >
+codemeter
+GenICamBrowser
+###############################
+
+
+
+## How-To Stream?
+
+    SS = Streaming Server
+
+    GT 1920:
+        read stream specs.
+        search VIMBA ... IP-based.
+
+    ndi-python
+        wrapper for NDI-SDK
+    ffmpeg as RTMP-SS
+    nginx
+        nginx-rtmp-module
+        linux SS
+    openCV
+        VideoCapture(  protocol://host:port/script_name?script_params|auth )
+    Gstreamer
+        QT
+        Vimba plugin?
+
+    obs-studio/jammy 27.2.3+dfsg1-1 amd64
+        recorder and streamer for live video content
+        can use NDI?

dox/misc2

+vimba: GVSPAdjustPacketSize - find max size automatically
+	if size < 1500
+		> enable jumboframes
+
+check:
+	vimbaviewer > stream > statistics
+	StatFramesDelivered / StatPacketsReceived != 0
+	StatFramesDropped == 0
+
+	run as root. (or workaround p159 to start app as root and drop rigths immediatly afterwards)

dox/notes

+## SW from tboy old workstation
+https://ctrax.sourceforge.net/
+	walking fly tracker
+HOBOWare Lite
+	temperature logger
+StreamPix5
+	realtime digital video recording to PC memory or hdd
+	batch processor
+	https://www.norpix.com/products/streampix/streampix.php
+
+Matlab (.m files)
+any2ufmf
+fviewflytrax
+avidemux
+yEd - graph editor - .graphml files
+batchprocessor
+	process sequence files to avi
+ssdcleanup
+
+##buy?
+https://www.alliedvision.com/en/products/accessories/tripod-adapter/
+
+###############################
+## Emilio
+###############################
+> !! if beetle runs in circle it is in "escape mode" which doesnt represent "natural" behaviour (explore, quick move from a to b)
+	-> think about different setup. Bigger Arena?
+> fps can be low. Try 3!
+	Depends on movement speed and estimated error
+	calc error by comparing distance of 40fps with 3fps
+> duration of video can be short. eg 10 minutes.
+	-> no need for many fridges
+
+###############################
+## Software A - Frame grab
+##############################
+
+# setup Vimba
+	> see Vimba_installation_under_Linux.pdf
+	> download and unpack Vimba SDK
+	> tar -xzf ./Vimba.tgz
+	> sudo ./VimbaGigETL/Install.sh
+
+## SETUP GT1920C:
+> connect lap and cam directly via ethernet
+> set MTU to 8228 (jumbo frames/packets)
+> set fixed IP for eth-adapter first and then cam (use Vimbaviewer -> force IP)
+	eth 169.254.100.1
+	cam 169.254.x.x # on restart will pick random IP...
+
+	mac
+		000f310338D3
+		000f310338D4
+	sub 255.255.0.0
+  (gat 0.0.0.0 local / none)
+	-> ip address of each adapter needs to be on a unique subnet
+	-> for multiple cams calc bandwith and use switch
+
+# What bandwidth do i have? Do i need multiple ports?
+bandwith = fps * pixel format(bpp) * resolution (* ncams)
+StreamBytesPerSecond = 17 * 3 * 1936 * 1216 * 1 = 8 456 448 ~= 8,4 MBps < 125MBps
+
+	1. Determine max_speed with highest fps!
+	2. Take max_speed and reduce fps so it still fits 2*max_speed
+		-> subsample same video ?
+	3. calc mean_err through comparing 1. and 2. -> add to 2. as it will be lower.
+
+	!! exposure and fps: on 10fps exposure can't be more then 100ms!
+	!! exposure and fps: on 17fps exposure can't be more then 59ms!
+	Best practice: set gain to lowest possible val and increase exposure as needed
+	!! if you use more than one cam on one interface, the available bandwidth has to be shared between interfaces.
+
+###############################
+# bandwidth calculations for Alvium G1 240C
+MAX BANDWITH for Gigabit ethernet port ~= 125 Mbps
+max res: 1936x1216
+max fps: 49
+pixelformat: RGB8  > different options. eg 10bit/12bit RGB/MONO.
+	1936 * 1216 * 49 * 1 ~= 115,3 MBps >> MONO8 @ maxFPS
+	1936 * 1216 * 17 * 1 ~= 40,0 MBps >> MONO8 @ 17FPS
+		@ 1 Min -> 2.4GB
+		@ 30 Mins -> 144GB
+		with 60 recordings: 8.6TB
+	1936 * 1216 * 17 * 3 ~= 120,1 MBps >> RGB8 @ 17FPS
+		@ 1 Min -> 7.2GB
+		@ 30 Mins -> 216.1GB
+		with 60 recordings: 13 TB
+
+	1936 * 1216 * 10 * 3 ~= 70,6 MBps
+		@ 1 Min -> 4.2 GB
+		@ 30 Mins -> 127.1 GB
+		with 60 recordings: 7.6TB
+
+Storage:
+ws1:
+	2TB: 2*1TB (7200RPM)
+	8Gb DDR3 RAM
+	Intel Xeon 3.6Ghz (4 cores)
+ws2: 4TB: 3 (7200RPM = 6GB/s!) + 1
+	8GB DDR3 RAM
+
+default bandwidth:115MBps
+
+Save "reasonable" settings in XML.
+If dark, set ExposureTimeAbs
+Q: how to set fps to 3?
+
+
+#####################################
+## Background Substraction - BGS
+####################################
+
+
+#define bgs_register(x) static BGS_Register<x> register_##x(quote(x))
+## >> glue together macro?
+quote() adds ""
+
+bgs_register(Tapter)
+>> static BGS_Register<Tapter> register_Tapter("Tapter")
+
+/usr/include/opencv4/opencv2/opencv.hpp
+PCA?
+
+
+> difference
+	virtual();
+	virtual(){ /*empty*/ }
+	virtual() = 0; #pure virtual
+
+> also difference
+	> virtual dtor(): if pointer to base-class deletes object
+	> pure virtual dtor(): need to also define function body, cuz dtor is special function whis is not overriden
+	> interface class (needs pure virtual??)
+	> abc - abstract base class. can't be instantiated anymore
+	> abc <> interface?
+
+
+	// IplImage is oldskool mat and not supported anymore..
+
+	> use smartpointer like so:
+	auto videoAnalysis = std::make_unique<VideoAnalysis>();
+ 		videoCapture = std::make_unique<VideoCapture>();
+      	frameProcessor = std::make_shared<FrameProcessor>();
+
+
+###########
+libarchive stuff
+	archive_read_xxx()
+	archive_write_xxx()
+	struct archive_entry
+
+huge workaround for corrupted files
+clock
+random
+command arg parser
+
+
+
+???
+#if CV_MAJOR_VERSION > 3 || (CV_MAJOR_VERSION == 3 && CV_SUBMINOR_VERSION >= 9)
+  IplImage _frame = cvIplImage(img_input);
+  frame = &_frame;
+#else
+  frame = new IplImage(img_input);
+#endif
+
+#smartpointer??
+#elif CV_MAJOR_VERSION >= 3
+      cv::Ptr<cv::BackgroundSubtractorMOG2> mog;
+#endif
+
+
+
+> What Tboy do... why did he do it?
+	> forked branch bgslib_qtgui_2.0.0
+	> Tapter
+			> adapter for model
+			> was probably copied from LBAdaptiveSOM.cpp
+		--> which is disabled in openCV4
+
+
+Which Background Subtraction Algo to use??
+	median, mean, framedifference
+		+ simple, fast,
+		- not robust if light/bg changes
+		- slow changes ?
+	> adaptive bg?
+	fuzzy?
+	mixture
+
+
+NAMES
+	Kernel?
+	LBSP?
+	Multilayer?
+	Sigma-Delta?
+	Vibe, T2F ,dp ,lb ,vumeter?
+	choquet, sugeno, zivkovic, pratimediod, LOBSTER
+
+Test/Use most common >> Ground Truth
+	Frame Difference
+	WeightedMovingMean / Variance
+	LBAdaptiveSOM
+	MOG2 (Mixture Of Gaussian) MixtureOfGaussianV2.h
+	KNN (K Nearest Neighbour)
+		> fast for small fg obj
+		> TRY!
+	FuzzySugenoIntegral.h
+
+	LSBP - Local Binary Similarity Patterns - (2013)
+	LSBP-based GSoC ?
+	SuBSENSE: improved spatiotemporal LBSP + color features (2014)
+
+	Combineable with
+		ROI
+		Canny Edge Detection
+
+
+> bg modeling to update BG (eg moving trees) > pixel with threshold
+> optic flow (camera is also moving. ) > vectoral estimation of own movement
+
+
+features
+	edge
+		canny edge detector + calc contour
+		> https://en.wikipedia.org/wiki/Canny_edge_detector
+	roi
+		crop
+	color
+		RGB - not so robust by itself (sensitive to illumination, shadows, oscillations ...)
+		YUV
+		YCrCb - brightness, chroma, color
+	texture
+		robust to illumination and shadow
+		eg Local Binary Pattern (LBP)
+
+https://github.com/murari023/awesome-background-subtraction (2021 new stuff!)
+
+https://learnopencv.com/background-subtraction-with-opencv-and-bgs-libraries/
+http://docs.opencv.org/2.4/doc/tutorials/imgproc/gausian_median_blur_bilateral_filter/gausian_median_blur_bilateral_filter.html
+https://hackthedeveloper.com/background-subtraction-opencv-python/ #mog2 + knn in python
+https://docs.opencv.org/4.3.0/d4/dd5/classcv_1_1bgsegm_1_1BackgroundSubtractorGSOC.html#details #GSOC LSBP ALGO from openCV bgsegm.hpp
+
+https://openaccess.thecvf.com/content_cvpr_workshops_2014/W12/papers/St-Charles_Flexible_Background_Subtraction_2014_CVPR_paper.pdf
+https://www.scitepress.org/Papers/2018/66296/66296.pdf #vehicle tracking latvia. 2018, BackgroundSubtractorMOG, BackgroundSubtractorMOG2 (zivkovic)
+https://www-sop.inria.fr/members/Francois.Bremond/Postscript/AnhTuanAVSS14.pdf  2014
+https://arxiv.org/pdf/1803.07985.pdf # visual animal tracking (2018)
+https://arxiv.org/pdf/1507.06821.pdf # Multimodal Deep Learning for Robust RGB-D Object Recognition (2015)
+https://towardsdatascience.com/background-removal-with-deep-learning-c4f2104b3157?gi=2ef3a5272e5d (2017 Background removal with deep learning)
+
+https://opencv.org/courses/ #xpensive ai course
+https://www.fast.ai/ #free ai course
+
+Build with Python or C++?
+
+
+##################
+# computervision #
+##################
+background subtraction (bgs)
+segmentation
+	Semantic Segmentation (ai)
+detection (feature, object)
+classification (category recognition)
+
+Challenges: Occlusion, (Sensor-)Noise, changing external conditions( lighting, Shadows, fog, reflection )
+
+> pre-training if lack of data
+> corrupt data to guarantee robust learning
+
+######
+# AI #
+######
+Convolutional Neural Networks (CNNs)
+	https://www.researchgate.net/publication/337401161_Fundamental_Concepts_of_Convolutional_Neural_Network (2020 37p)
+		> Kernel
+		> filter?
+		> preprocessing > Training > Parameter init > regularization > optimize
+
+
+RGB-D - RGB + depth >> eg Kinect-Sensors
+KNN - k-nearest neighbors algorithm
+Monte Carlo tree search algorithm (alphaGo...)
+
+RGB-D descriptor that relies on a K-Means
+HMP - hierarchical matching pursuit ( hierarchical sparse-coding method; learn features from multiple channel input)
+
+encoding depth information into three channels (HHA encoding) feature hierachy
+cascade of Random Forest classifiers that are fused in a hierarchical manner ?? #Random Forest
+
+metrics:
+	recall - how many relevant items are retrieved?
+	precision - how many retrieved items are relevant?
+	> https://en.wikipedia.org/wiki/Recall_(information_retrieval)
+
+?
+automatically learn a fusion strategy for the recognition
+task – in contrast to simply training a linear classifier on
+top of features extracted from both modalities
+
+MISRE - Multiple Input Structures with Robust Estimator
+gradient-based learning
+	> MNIST supervised image classification
+		MNIST - large db of hand-written digits (used for ML and ImagePRocessing)
+	> also see classifiers: https://en.wikipedia.org/wiki/MNIST_database#Classifiers
+multimodal learning
+
+the parameters of all layers were adapted using a fixed learning rate schedule
+
+At test time the task of the CNN is to assign the correct class label to a previously unseen object instance.
+
+Tasks:
+Classification, clustering, regression, Summarization, Categorization, Natural language processing,
+
+##################################
+# STAT
+##################################
+Regression
+Hadamard Product
+Bernoulli Distribution
+Discrete Uniform Distribution
+##################################
+# CMAKE
+##################################
+sublime: install package CMAKE (syntax hilight)
+apt install libarchive-dev python3-pybind11
+
+##################################
+
+
+
+ init(img_input, img_output, img_bgmodel);
+
+#if CV_MAJOR_VERSION > 3 || (CV_MAJOR_VERSION == 3 && CV_SUBMINOR_VERSION >= 9)
+  IplImage _frame = cvIplImage(img_input);
+  frame = &_frame;
+#else
+  frame = new IplImage(img_input);
+#endif

dox/opencv

+
+point2f(y,x) # inverted!
+BGR 	#not rgb ...
+Scalar = 4 element vector
+CV_RGB(r, g, b) #from bgs
+
+Types:
+	#depth
+	CV_8U 	unsigned char
+	CV_8S 	char
+	CV_16U 	unsigned short
+	CV_16S 	short
+	CV_32S 	int
+	CV_32F 	float
+	CV_64F 	double
+	# + channels C1..4 	eg RGBA:
+	# eg Mat M(2,2, CV_8UC3, Scalar(0,0,255));
+	0 to 255 for CV_8U images
+	0 to 65535 for CV_16U images
+	0 to 1 for CV_32F images
+
+
+
+# Camera Calibration:
+########################
+	distortion_coefficients - 5 values
+	camera_matrix - 3x3 matrix - eg focal length etc.
+
+	different methods:
+		https://docs.opencv.org/4.x/d7/d21/tutorial_interactive_calibration.html
+		https://docs.opencv.org/4.x/d6/d55/tutorial_table_of_content_calib3d.html
+
+		# using chess board, to get values
+		https://github.com/abidrahmank/OpenCV2-Python-Tutorials/blob/master/source/py_tutorials/py_calib3d/py_calibration/py_calibration.rs
+
+
+
+# Matrices
+########################
+	Fill matrix with random values
+		Mat R = Mat(3, 2, CV_8UC3);
+		randu(R, Scalar::all(0), Scalar::all(255));
+
+	Formatted output
+		cout << "R (csv)     = " << endl << format(R, Formatter::FMT_CSV   ) << endl << endl;
+		#sa FMT_C/PYTHON/NUMPY/CSV
+
+	InputArray = vector or Mat
+
+	type()
+	create(r,c,t)
+	copyTo()
+	clone() for deep copy
+	cv::Mat F = cv::Mat::ones(3, 4, CV_32FC1) * 3; //all 3's
+
+	traverse: https://programmersought.com/article/72762264465/
+
+##roi - region of interest
+	x, y, w, h
+
+	// roi as subset of full data image
+	Mat D (A, Rect(10, 10, 100, 100) ); // using a rectangle
+	Mat E = A(Range::all(), Range(1,3)); // using row and column boundaries
+
+	locateROI, adjustROI,
+
+
+# CommandLineParser
+	@ -> positional arg
+	no default value -> has_XX
+	else: get<T>("XX")
+	<none> dflt value to ensure strings arent ""
+
+# MISC
+########################
+	glob( dir, file )
+
+	randu() # https://docs.opencv.org/4.x/d2/de8/group__core__array.html#ga1ba1026dca0807b27057ba6a49d258c0
+	cvtColor(img, img, COLOR_BGR2Luv); #convert color
+
+	sounds interesting:
+	selectROI, selectROIs, reduce, qt, dilate, erode,
+	convexhull, findcontours, checkChessboard, calibrateCamera
+	hough ?
+	hu-invariants, centroid
+	moments (weigthed avg of pixel intensities)
+		spatial <> central <> central normalized
+
+	randPattern
+
+
+BS:
+https://docs.opencv.org/4.x/da/d5c/tutorial_canny_detector.html
+https://docs.opencv.org/4.x/d1/dc5/tutorial_background_subtraction.html
+https://web.archive.org/web/20140418093037/http://bmc.univ-bpclermont.fr/
+https://web.archive.org/web/20140221195750/http://docs.opencv.org/trunk/doc/tutorials/video/background_subtraction/background_subtraction.html
+https://www.pyimagesearch.com/2020/07/27/opencv-grabcut-foreground-segmentation-and-extraction/
+https://learnopencv.com/applications-of-foreground-background-separation-with-semantic-segmentation/
+https://docs.opencv.org/4.x/d2/d55/group__bgsegm.html
+https://docs.opencv.org/4.x/d5/de8/samples_2cpp_2segment_objects_8cpp-example.html#_a15
+
+tuts:))
+https://docs.opencv.org/4.x/d6/d00/tutorial_py_root.html
+https://datahacker.rs/opencv-thresholding/
+
+# median frame as bg + frame difference
+https://learnopencv.com/simple-background-estimation-in-videos-using-opencv-c-python/
+
+https://learnopencv.com/contour-detection-using-opencv-python-c/
+https://learnopencv.com/deep-learning-with-opencvs-dnn-module-a-definitive-guide/
+
+moments
+https://docs.opencv.org/4.x/d0/d49/tutorial_moments.html
+
+#BGS
+https://docs.opencv.org/4.x/d8/d38/tutorial_bgsegm_bg_subtraction.html
+
+
+
+# alliedvision-vimba-sdk
+#######################
+	AsynchronousGrab example > to use with opencv
+
+	/tmp/mozilla_sugu0/Vimba_installation_under_Linux-1.pdf
+
+	C-api
+	https://www.ansatt.hig.no/ares/Support/Camera%20drivers/AVT/Vimba/1.1/VimbaC/Documentation/Vimba%20C%20Manual.pdf

dox/todo_ct

@@ -193,8 +193,39 @@ X) HPC - High Performance Cluster
 
 Z) laptop/fon maintenance
 ###############################
+	> sync+manage bookmarks of different FIREFOXES. Delete one.
+	> add symbols to 'cmds' for quick copy-paste
+	> sub: alt+5 can't toggle to 5th pane.
+		shortcut for toggling panes via number and/or left-right
+		shortcut for replace next in an intuitive manner (no mouse!)
 
 
+## NOTES
+###############################
+"i conduct experiments in a lab, that i build up in a prestigious scientific institute"
+"as a craftsman, i hone my skill to build/create things"
+"i use my skills to earn €"
+"i live and work with integrity"
+-------------------------------
+4-5h/d @ 4-5/w -> finetune DW/SW
+get feedback (occassionaly)
+
+milestone 1: build up hardware
+	> fridges,cams,light,arena,workstation,
+milestone 2: get videodata
+	> 2.1 via vv
+	> 2.2 via own SW!
+milestone 3: collect all data using 1 camunit
+milestone 4: collect all data using 6 camunits
+milestone 5: conduct experiments
+milestone 6: analyze I - get simple vars
+	movement: calc coordinates (roi,bgs substraction,bgs midpoint,..)
+	aggregate CSV (coord + time + temp/rH)
+milestone 7: analyze II - get more vars
+	> calc speed,angles,distance
+
+> 5 & 6 could be swapped!
+
 
 
 Done