Granted Patent B2

US 12,641,348 · App. 18/862,971 · Granted May 26, 2026

Inventors: Henrik Jörntell (Lund, SE); Udaya Bahskar Rongala (Lund, SE); Elias Högbom Aronsson (Lund, SE)

Assignee: IntuiCell AB

H04N25/60G06N3/049G06V10/50G06V10/62H04N23/54H04N23/61H04N23/675H04N25/47G06V10/75G06V20/69H04N23/617H04N25/707

Abstract

Claims (52)

1 . A data processing system for processing pixel data, configured to receive pixel data, comprising central pixel data and neighboring pixel data, from each image of a sequence of images captured by an imaging device as system input and configured to have a system output, the system comprising:

a plurality of input nodes, each input node configured to receive pixel data from a respective pixel as input, each input node comprising an input node leaky integrator having a first time constant and a weight for the input, and each input node being configured to produce an input node output by applying the input node leaky integrator and a respective weight to the input; and

an output node, comprising an output node weight and a multiple input leaky integrator having a second time constant,

wherein the output node is configured to:

receive each of the input node outputs,

receive pixel data from the central pixel,

combine the pixel data from the central pixel with the output node weight to produce weighted central pixel data,

apply the multiple input leaky integrator to the weighted central pixel data and to each of the input node outputs, and

produce the system output as a combination of the weighted central pixel data and each of the node outputs; and

wherein the second time constant is smaller than the first time constant, and wherein the system output is indicative of a contrast.

2 . The data processing system of claim 1 , wherein the method further comprises obtaining, by applying the leaky integrators and feed the data processing system with pixel data from multiple images, a temporal differential signal indicative of a contrast between the pixels in the same position of the different images.

3 . The data processing system of claim 1 , wherein the method further comprises obtaining, by inputting data from a central pixel and data from neighboring pixels to the data processing system, a spatial differential signal indicative of a contrast between the central pixel and the neighboring pixels in the same image.

4 . The data processing system of claim 1 , comprising a threshold unit configured to receive the system output, wherein the threshold unit is configured to compare the system output with a threshold and wherein the threshold unit is configured to output a signal indicative of a detected event.

5 . The data processing system of claim 1 , wherein the weight of an input node is larger the closer the central pixel is to the pixel.

6 . The data processing system of claim 1 , wherein the sum of all weights of the input nodes are equal to the output node weight.

7 . A device comprising the data processing system of claim 1 and an imaging device, the imaging device being configured to capture the pixel data and to transmit the captured pixel data to the data processing system.

8 . A device comprising the data processing system of claim 1 and an imaging device, the imaging device being configured to capture the pixel data and to transmit the captured pixel data to the processing system, wherein the imaging device is a multiphoton microscope, a laser confocal microscope or a digital video camera.

9 . An arrangement comprising:

the data processing system of claim 1 for each of the pixels of the pixel data;

a database comprising images of known objects; and

a post-processing unit configured to receive the system output from each of the data processing systems, configured to compare the system outputs to the images of the known objects, and configured to identify an object present in the pixel data, based on the comparison, as the known object with the image differing the least from the system output.

10 . The data processing system of claim 1 , wherein the system output produced as a combination of the weighted central pixel data and each of the node outputs comprises differential data generated by subtracting each of the input node outputs from the weighted central pixel data.

11 . A computer-implemented method for processing pixel data, the method comprising:

receiving pixel data comprising data from a central pixel and data from neighboring pixels from each image of a sequence of images as system input;

providing each of the pixels as input to a respective input node;

applying a respective input node leaky integrator, having a first time constant, and a respective weight to each of the inputs, thereby producing an input node output;

receiving, by an output node, each of the input node outputs and pixel data from the central pixel;

combining the pixel data from the central pixel with an output node weight, thereby producing weighted central pixel data;

applying a multiple input leaky integrator having a second time constant, the second time constant being smaller than the first time constant, to the weighted central pixel data and to each of the input node outputs, thereby combining the weighted central pixel data and each of the input node outputs to produce a system output; and

utilizing the system output to indicate a contrast.

12 . A computer program product comprising a non-transitory computer-readable storage medium storing instructions, which, when executed on at least one processor of a processing device, cause the processing device to carry out the method of claim 11 .

13 . A computer-implemented method for auto-focusing of an imaging device, the method comprising:

receiving images of a sequence of images, each image comprising pixel data;

determining of a preliminary region of interest of an image based on a user input;

selecting a preliminary region of interest, based on the determined size;

providing each of the pixels of the preliminary region of interest as input to a respective input node;

applying a respective input node leaky integrator, having a first time constant, and a respective weight to each of the inputs, thereby producing input node outputs;

receiving, by an output node, each of the input node outputs and pixel data from the central pixel;

combining the pixel data from the central pixel with an output node weight, thereby producing weighted central pixel data;

applying a multiple input leaky integrator having a second time constant, the second time constant being smaller than the first time constant, to the weighted central pixel data and to each of the input node outputs, thereby combining the weighted central pixel data and each of the input node outputs to produce a system output;

storing at a first position of a memory the system output and at a second position of the memory a position of the preliminary region of interest if the system output is higher than the value currently stored at the first position of the memory;

shifting the preliminary region of interest one pixel step;

repeating the steps of receiving images, determining, selecting, providing, applying, receiving each of the input node outputs and pixel data from the central pixel, combining, applying, storing, and shifting until a stop criterion is met;

setting the position stored at the second position of the memory as a position of a region of interest;

scanning through a focal range to find the highest contrast value for the region of interest; and

utilizing the focal point at the highest contrast value, thereby focusing the imaging device.

14 . The computer-implemented method of claim 13 , wherein the stop criterion is that all possible regions of interest within the pixel data has been checked.

15 . The computer-implemented method of claim 14 , wherein the stop criterion is that the preliminary region of interest has reached an end position.

16 . The computer-implemented method of claim 13 , wherein the imaging device is a digital video camera.

17 . The computer-implemented method of claim 13 , wherein the preliminary region of interest is an region of interest located in one of the images.

18 . The computer-implemented method of claim 13 , wherein the system output produced as a combination of the weighted central pixel data and each of the node outputs comprises differential data generated by subtracting each of the input node outputs from the weighted central pixel data.

19 . The computer-implemented method of claim 13 , wherein the method is implemented as a hardware-implemented method.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (37)