Systems and methods for processing image data associated with line detection

Abstract

In a particular embodiment, a method includes receiving line segment data at a processing core. The line segment data is associated with multiple candidate line segments associated with a first group of pixels of an image. The line segment data includes an angle value and / or a distance value for each of the multiple candidate line segments. The method further includes identifying, at the processing core, a set of line segments of the multiple candidate line segments by comparing angle values and / or distance values associated with the multiple candidate line segments. The method also includes determining, at the processing core, a representative line segment based on the set of line segments of the multiple candidate line segments. The method further includes storing, by the processing core, line segment information based on the representative line segment.

Description

I. FIELD[0001]The present disclosure is generally related to processing image data to detect a line included in an image.II. DESCRIPTION OF RELATED ART[0002]Advances in technology have resulted in smaller apparatuses and more powerful computing devices. For example, there currently exist a variety of portable personal computing devices, including wireless computing devices, such as portable wireless telephones, personal digital assistants (PDAs), and paging devices that are small, lightweight, and easily carried by users. More specifically, portable wireless telephones, such as cellular telephones and internet protocol (IP) telephones, can communicate voice and data packets over wireless networks. Further, many such wireless telephones include other types of devices that are incorporated therein. For example, a wireless telephone can also include a digital still camera, a digital video camera, a digital recorder, and an audio file player. Also, such wireless telephones can process e...

AI Technical Summary

Benefits of technology

[0005]The GPU is configured to process image data such that an amount of histogram data (e.g., a size of a histogram) generated by the GPU fits within a cache memory, such as a level 2 cache memory or a level 2 and a level 3 cache memory, associated with the GPU. For example, an image may be divided into a plurality of tiles (e.g., multiple groups of pixels) and the GPU may generate histogram data for each tile. The GPU may further use one or more reference points to determine distance values when generating one or more angle and distance pairs to be included in histogram data for a particular tile. By dividing an image into multiple tiles and using one or more reference points to process each tile, the histogram data may be stored in the cache memory as opposed to a main memory, which enables faster access of the histogram data to process the histogram data to identify one or more candidate line segments.

[0006]When tiling is used to process the image, detected line segments within each tile may be consolidated prior to merging detected line segments across multiple tiles. Consolidating detected line segments within a tile may lead to improved accuracy of a resultant line segment detected within the tile. Additionally, by consolidating the detected line segments, a number of detected line segments to be processed by an inter tile merger may be reduced; thus, a speed of identifying one or more global lines associated with an image may be increased.

[0009]In another particular embodiment, a computer-readable medium storing instructions that are executable by a processor to cause the processor to perform operations including receiving line segment data associated with multiple candidate line segments associated with a first group of pixels of an image. The line segment data includes an angle value for each of the multiple candidate line segments, a distance value for each of the multiple candidate line segments, or a combination thereof. The instructions further cause the processor to perform operations including identifying a set of line segments of the multiple candidate line segments by comparing angle values associated with the multiple candidate line segments, distance values associated with the multiple candidate line segments, or a combination thereof. The instructions further cause the processor to perform operations including determining a representative line segment based on the set of line segments of the multiple candidate line segments and determining line segment information based on the representative line segment. The line segment information includes at least one end point coordinate associated with the representative line segment.

[0010]One particular advantage provided by at least one of the disclosed embodiments is that by performing the candidate line segment detection at a first processor (e.g., the GPU or the DSP) and by performing the line merging to merge multiple candidate line segments at a second processor (e.g., the CPU), different processors may be selected that are best suited for a particular task. By dividing the processing tasks between multiple processors that are each suited for their respective tasks, power consumption may be reduced in a system or device that uses multiple processors as compared to a system that uses a single processor for candidate line segment detection and for line merging. Another particular advantage provided by at least one of the disclosed embodiments is that by being able to save the histogram data into a cache memory, an amount of processing time and an amount of power consumed may be reduced as compared to a system that saves the histogram data to a main memory. Reducing the amount of processing time and the amount of power may enable implementation of the Hough transform (to detect one or more lines in an image) by a mobile device. Additionally, by dividing the processing tasks between the multiple processors, different stages (e.g., processing tasks) may be pipelined and a processing throughput of the multiple processors may be increased.

Problems solved by technology

The 2D histogram is related to a size of the image and may also be related to a maximum length of a detected line and, for large images, the 2D histogram may consume a large amount of memory space.

Additionally, a processor of the wireless device may have to perform an exhaustive and time consuming search of data within the memory space to detect one or more lines based on the 2D histogram.

Because of the large amount of memory space and the processing power needed to detect the one or more lines, implementing the Hough Transform is problematic when performed by a mobile device (e.g., the wireless device) which has limited memory space and limited processing power.

Images