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 ...


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

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 [1]. But even a simple low-pass filter may be sufficient depending on how bad the non-stationarity ...


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

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

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

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

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

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 ...


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

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

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

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

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 ...


1

You can calculate the mean of your nonzero signal, then substract it to the non-zero mean signal and calculate the envelope as you did before. That will give you the envelope of the signal for the zero mean signal, but if you want to recover the envelope for the non-zero mean signal, then you just have to add to this envelope the initially calculated mean.


1

You may try an OCR detector like Teseract with OpenCV: https://github.com/tesseract-ocr Train the Teseract algorithm with text samples obtained from the numbers you want to detect and it will work. EDIT: If you want a similar implementation of what you want you may check this: http://answers.opencv.org/question/10985/how-can-i-determine-the-location-of-...


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),...


1

Take a look at this stackexchange post: Vein extraction from this image There, I talk about a curvi-linear structure detector, from Steger. Moreover, an extension is given here for Gaussian profiles: Carsten Steger, Unbiased extraction of lines with parabolic and Gaussian profiles, Computer Vision and Image Understanding, Volume 117, Issue 2, ...


1

In your provided image the central axis is straight and have the same color throughout, therefore a Hough operator can detect this.


1

There are two things I know of which will cause a problem: Some dance music just isn't in any key. It's just sounds lumped together until it sounds great. The kick drum is the loudest thing but isn't always in a particular key. Often it just decays in frequency. There's been a trend recently for kick drums to be tuned to the track, but it's not always ...


1

Since you have convolution and dilation you can use the Laplacian of Gaussian blob detector to detect the blobs and dilation to find the centre points. In MATLAB: sigma = 3; % Filter image with LoG I = double(rgb2gray(imread('NCxQ8.jpg'))); h = fspecial('log', sigma*6, sigma); B = -imfilter(I,h); imagesc(B); pause; % Threshold B(B < 5) = 0; imagesc(B); ...


1

This is not a complete and comprehensive answer but provides some examples showing the key features in a linear and non-linear equalizer and also clarifies consideration for feedforward vs feedback structures in equalizers. Linear equalizers are typically feed-forward in structure, and linear as the output is a linear combination of scaled and delayed ...


1

You should know the orientation of the phone because the axis signum must be the same of the car motion. Assuming the axis signum is correct you can filter the accelerometer signal in lowpass, to clean the high frequency noise and then see the signal signum to detect if it is a break $a(t_i)<0$ or an acceleration $a(t_i)>0$. You should try to ...


1

When brakes are applied, the acceleration along the direction of motion will reverse sign. For example, if you position your phone such that the z-axis of the accelerator is in the direction of gravity axis(i.e. facing earth), then the acceleration along z-axis is -g. One the other hand if the negative z-axis is aligned with g, then z-axis of accelerometer ...


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