# Tag Info

13

Here is my solution, it is close to @Yoda's idea, but I changed some steps. Mark all pixels such that there are at least 6 pixels in their 7x7 neighborhood Remove all blobs, but the largest Fill holes Apply edge detection Find circle using Hough transform Here is the relevant Matlab code. I am using Hough transform for circles .m file in my code. function ...

10

It's fairly straightforward to do it using image processing. The following is a proof of concept in Mathematica. You'll have to translate it to MATLAB. First, trim the axes and keep only the image part of it. I call this variable img. Binarize the image and dilate it, followed by a filling transform. I also remove stray small components that are not ...

8

Here is what I did for a client (What you are asking is the same). Assuming that you have access to certain type of a pattern on the image (or the center of the hole), you could always detect the template to obtain the location of a possible unwarp: Note that in the transformed image, two region of interests are defined and the region within which we would ...

6

A recording originally at 8kHz and digitally upsampled to 16kHz will have almost no energy in the 4-8kHz range (whatever is here is due to imperfections in the filters used for the upsampling process). I would just use a 4kHz and 5.5kHz high pass; and use a threshold on the signal energy at the output of these filters. ... Unless your recordings are ...

4

That looks a lot like an exponentially decaying sinusoid. What you are primarily interested in is the decay rate. Where it ends would then have to be defined as when it reached some threshold level. Create a subsequence consisting of the peak values and the negative values of the troughs. This should give you a nice exponential decay function. Then ...

3

One way to do this is to look at modeling your signal: $$x[n] = x_h[n] + x_n[n]$$ where $x_h$ is the hissing sound and $x_n$ is the noise. If you can say that $x_n$ is modeled as: $$x_n[n] = \sum_{k=K_1}^{K_2} a_k \sin(k\omega_0 n + \phi_k)$$ where $K_1$ is the lowest harmonic of frequency $\omega_0$ that makes it through your high pass filter, $K_2$ is ...

3

The formula you need, which I don't see in the scanned pages, is the N-dimensional Gaussian distribution of the received vector given that the signal $s_m$ was transmitted: $$f(\vec{r}|s_m)=\frac{1}{(\pi N_0)^{N/2}}\exp\left[-\frac{\sum_{j=1}^N(r_j-x_{mj})^2}{N_0}\right]\tag{1}$$ The maximum likelihood receiver seeks to maximize this conditional ...

3

The "best" detector is a highly subjective subject, and there is (in my opinion) not a definitive answer here. I work in radar processing and I've used everything that you've mentioned in one form or another. All of these CFAR methods are tools, and all of them have good/bad applications. For instance, asking what the "best" wrench is in the toolbox highly ...

3

Part of your misunderstanding comes from the fact that there are many ways in which the radar signal processing chain is implemented. Depending on the type of radar, targets of interest, hardware, etc., some methods are more appropriate than others. We will consider pulsed-Doppler radar here. In the chain you describe: In modern pulse-Doppler systems using ...

3

$\DeclareMathOperator{\sgn}{sgn}$ The modulating signal in AM is $$s(t) = C + a(t)\text,$$ where $a(t)$ is the (audio) amplitude, and $C$ is a constant so that $s(t) \ge 0 \;\forall t$. (Otherwise, your audio amplitude would just frequently "switch" the wave's sign, not really modulate the envelope.) That means, $C > - \min_t(s(t))$. Therefore, the ...

2

First, de-noise the waveform using a technique suitable for non-stationary signals. Admittedly, the spectrum of the signal doesn't change too much over time. There are efficient iterative de-noising algorithms for this purpose, such as basis pursuit de-noising . But even a simple low-pass filter may be sufficient depending on how bad the non-stationarity ...

2

This is clearly not an easy task. The problem is, if you want a more-or-less accurate count, then you need to turn to advanced algorithms (and maybe use 2 cameras, or a kinect). If you can't afford to take this path, then you need to try simpler options. Personally, I would try the following: detecting skin pixels, segmenting the image with respect to ...

2

You should use elements which are a power of 2, for easy and faster computation. I'll say, start with 8x8, so you can only scale up. And if you have to look only at some portions of this image, then you can crop the original one.

2

This is a saddle point. I would suggest using derivative operators to spot such discontinuities. In fact, Haralick presents a broad overview of these methods in his Topographic Primal Sketch. The use of approximate Facet model would give you a speed boost. I used them for edge detection here. There is also one implementation available here. Even though ...

2

Although it looks like it's not being actively maintained, you might check out "aubio" to see if it will meet your needs : http://aubio.org/ aubio is a tool designed for the extraction of annotations from audio signals. Its features include segmenting a sound file before each of its attacks, performing pitch detection, tapping the beat and producing midi ...

2

I have used Laplacian of a gaussian filtered image with sigma value of 3. I have thresholded the LoG image with a high-pass filter. I have used gray closing morphologic operator. I have filtered the blobs according to their area. There are several more ways to do it depending on the images, conditions(sea), illumination, ships etc. For this image, non-color ...

2

Since you're after a filter which emphasizes abrupt changes you should use High Pass Filter. The issue is you'd be also sensitive to noise. Hence one way to do it is to apply High Pass Filter on slightly blurred image (Which actually results in a Band Pass Filter). One easy choice would be using the Gradient of The Gaussian Filter. Why is it? Because it is ...

2

The detection task is: Given an image $I$, does it contain a sub-image $S$ (or an object $S$)? There are several things that can happen: $I$ contains $S$ and the detector says $I$ contains $S$ This is a True Positive: the statement is true, and the statement is positive ($S$ is there) $I$ contains $S$ and the detector says $I$ DOES NOT contain $S$ This ...

2

Intuitively, HSV is the place to easily define Skin Color Hues. Yet there is a broad work on that and even articles about the optimal Color Space for Skin Detection. Yet, you should have a look at OPTIMUM COLOR SPACES FOR SKIN DETECTION (Alternative at IEEE - Optimum color spaces for skin detection). According to them there is no difference in the ...

2

You can use Voice Activity Detector(VAD) for detecting the pauses in speech and there location(and duration). if your input signal is not very noisy and noise is not varying much you can use a fixed threshold on the energy(calculated for short frames, ex-20 ms), so if energy is above that threshold you declare that frame as speech else pause. if input signal ...

2

A 12-dimensional chromagram may not estimate pitch very well, given synthesized semi-tonal sounds that include lots of energy at multiple odd harmonics, as those harmonics will often end up in the wrong pitch class slots. If there's lots of tonal bass, low-pass filtering just above the primary range of the bass instrument/synth's fundamental might help ...

2

The step-to-step explanation in Eigenface seems quite clear to me. A covariance matrix is like an high-dimensional extension of the variance, which is computed by removing the average from your only sample. Yes, you remove the average face ($\operatorname{AF}$ from all images, but keep it preciously. Your cov(image1) definition seems weird to me, but ...

2

Resolution is (usually) referred to as the ability to distinguish two closely separated returns, not targets. The distinction is how far along the processing chain of the radar you are, resolution, given by the inverse of the bandwidth is often limited by the hardware (waveform generation, filters, amplifiers, sampling..) and the environment. While Radar ...

2

If you can detect the target separately , you have resolved the targets. If you resolved two targets, you have detected them too. In general you are totally right, radar can detect targets and in some cases can resolve several closely targets. Are radar resolution and detection capabilities not very tightly related? Usually they are related, but none of ...

2

I'll provide a slightly different perspective. Detection is usually measured against the noise and/or clutter statistics, so you end up with a detection probability which is a function of Signal to Noise Ratio. You will also have a probability of false alarm, which is a function of the noise/clutter statistics and the chosen threshold. In some radars ...

2

One approach could be to perform an FM-detection step (e.g. an atan2() operation followed by a first-order difference) to transform the waveform to measurements of the approximate received frequency versus time. Your FSK signal should then look like a binary-modulated baseband waveform. Then you can apply a nonlinearity to the signal to induce a discrete ...

2

To better deal with occlusions, my idea would be to separate this problem into detecting if: the 1st door is in position fully opened (1) the 1st door is in position fully closed (2) the 2nd door is in position fully opened (3) the 2nd door is in position fully closed (4) To tackle either of these problem, I would apply the following algorithm let's say ...

2

Theoretically you could separate your desired sound by ICA method or other blind source separation methods from the background music, then design a matched filter by your separated sound. The matched filter have high response when the desired pattern (which is your desired sound) exist in the input even when it buried in noise (background music). The ...

2

Hi: In statistics we call that the probability of type I error ( rejecting when true ) and type II error ( accepting when false ). The way it's done there is that, once you make an assumption about the distribution of the data ( i.e: normal, t, whatever ), you decide on the null and the alternative, along with what you want the P(type I error ) to be ( say 0....

1

First I would recommend filling in the contour of the toy - in case it looks like the one in the second image. You could do this by analyzing the hierarchy output from findContours: make white all regions having a parent or by using an iterative morphological operations (not directly implemented in OpenCV). Once the toy is nice and fat (not just the edge),...

Only top voted, non community-wiki answers of a minimum length are eligible