Abstract: A method for detecting and correcting transient faults, the method the steps of comprising obtaining (110) image data from a camera system, and processing (120) image data using a first image signal processor and a second image signal processor, to produce first and second output data. At least one statistical model is generated (130) based on at least the first and second output data and used to identify (140) whether a fault is present in the first output data. A correction value for the portion of image data is generated (150), wherein the correction value is an expected value based on the statistical models, and used to generate (160) updated output data. The updated output data is then outputted (170) to an output device.

Abstract: A method for detecting and correcting transient faults, the method the steps of comprising obtaining (110) image data from a camera system, and processing (120) image data using a first image signal processor and a second image signal processor, to produce first and second output data. At least one statistical model is generated (130) based on at least the first and second output data and used to identify (140) whether a fault is present in the first output data. A correction value for the portion of image data is generated (150), wherein the correction value is an expected value based on the statistical models, and used to generate (160) updated output data. The updated output data is then outputted (170) to an output device.

Abstract: A method for reducing artefacts caused by the presence of flicker during image capture. The method comprises performing image capture to produce image capture data corresponding to an image capture scene, the image capture data including a first image having a first exposure and a second image having a second exposure. The image capture data is processed to: (a) detect a discrepancy in the second image with respect to the first image; and (b) determine flicker indication data indicative of a presence of flicker in the second image. The discrepancy is corrected in dependence upon the flicker indication to produce a flicker-reduced version of the second image.

Abstract: Methods, apparatus and computer programs are provided for storing a set of sensor output images for multi-exposure high dynamic range processing to produce a processed image. The multi-exposure high dynamic range processing combines pixel values from one or more of the sensor output images to produce the processed image. In one example, a method comprises receiving from an image sensor a first sensor output image. The first sensor output image has a first exposure. The method also comprises receiving from the image sensor a second sensor output image. The second sensor output image has a second exposure different than the first exposure. First image pixels of the first sensor output image having pixel values which are unlikely to have a substantial contribution to the processed image are identified, and the amount of information stored in relation to the first image pixels is reduced on the basis of the identifying step.

Abstract: According to an aspect of the present disclosure, there is provided a method of image processing. The method comprises receiving image data. Image processing is applied to the image data, whereby to produce a processed image. The method then comprises producing consistency data associated with the image processing, wherein the consistency data is indicative of a consistency of at least one region of the processed image with the received image data. Both the processed image and the consistency data are used as inputs to a decision process of a computer vision system.

Abstract: A method for reducing artefacts caused by the presence of flicker during image capture. The method comprises performing image capture to produce image capture data corresponding to an image capture scene, the image capture data including a first image having a first exposure and a second image having a second exposure. The image capture data is processed to: (a) detect a discrepancy in the second image with respect to the first image; and (b) determine flicker indication data indicative of a presence of flicker in the second image. The discrepancy is corrected in dependence upon the flicker indication to produce a flicker-reduced version of the second image.

Abstract: Methods, apparatus and computer programs are provided for storing a set of sensor output images for multi-exposure high dynamic range processing to produce a processed image. The multi-exposure high dynamic range processing combines pixel values from one or more of the sensor output images to produce the processed image. In one example, a method comprises receiving from an image sensor a first sensor output image. The first sensor output image has a first exposure. The method also comprises receiving from the image sensor a second sensor output image. The second sensor output image has a second exposure different than the first exposure. First image pixels of the first sensor output image having pixel values which are unlikely to have a substantial contribution to the processed image are identified, and the amount of information stored in relation to the first image pixels is reduced on the basis of the identifying step.

Abstract: According to an aspect of the present disclosure, there is provided a method of image processing. The method comprises receiving image data. Image processing is applied to the image data, whereby to produce a processed image. The method then comprises producing consistency data associated with the image processing, wherein the consistency data is indicative of a consistency of at least one region of the processed image with the received image data. Both the processed image and the consistency data are used as inputs to a decision process of a computer vision system.

Abstract: A field programmable processor includes a regular array of processing elements, each of which is adapted to perform a fixed arithmetic function on packets of data. The processing elements are interconnected by an array of signal conductors extending adjacent the processing elements. Switching means are provided for selectively connecting the processing elements to the adjacent signal conductors so as to interconnect the processing elements. Program data representing desired processing element interconnections is stored, the switches are controlled in accordance with the stored program data to achieve the desired processing element interconnections. The packets of data are transmitted between the interconnected processing elements.

Abstract: A field programmable processor comprises a regular array of processing elements each of which is adapted to perform a fixed arithmetic function on packets of data. The processing elements are interconnected by an array of signal conductors extending adjacent the processing elements. Switching means are provided for selectively connecting the processing elements to the adjacent signal conductors so as to interconnect the processing elements. Program data representing desired processing element interconnections is stored, the switching means is controlled in accordance with the stored program data to achieve the desired processing element interconnections. The packets of data are transmitted between the interconnected processing elements.