Systems and methods for dynamic selection of high sampling rates for selected regions of interest - Patents.com

Abstract

A system and method including an imaging device and a processing unit is provided that allows for fast processing of image frame details. [Solution] The method includes performing a corresponding plurality of image frame processing cycles by an imaging device to acquire a plurality of data sets of a corresponding plurality of image frames, defining a specific region of interest (SROI) in each of at least some of the plurality of image frames acquired by the imaging device based on the data sets of the respective image frames by a processing unit, and acquiring at least one partial data set of the SROI by the imaging device during each of at least some of the plurality of image frame processing cycles, within the remaining time between the end of the image frame acquisition time and the end of the respective image frame processing cycle.

Description

[Technical Field]

[0001] The present invention relates to the field of increasing the sampling rate of imaging devices, and in particular to increasing the sampling rate for selected regions of interest within an image frame for better detection performance. [Background technology]

[0002] Processing image frame details, particularly the application of calculations to image frame data, inherently negates at least one of computational resources and computational time. The higher the resolution of the frame details, the greater the computational resources required and / or the slower the computational results. Applying high-resolution calculations only to a preselected region of the image frame (e.g., a region of interest (ROI)) may result in shorter processing results and / or a lower computational load. However, the selected ROI may coincidentally not include at least some image details that may be of high importance, thereby imbalancing the resulting benefit against the loss of important data.

[0003] For example, when processed image frames are captured from a forward-looking imaging device on a moving train (e.g., to provide advance warning of threatening obstacles), it is necessary to process the details of the image frames quickly while ensuring that the details contained in the area are contained in an area surrounding the rails ahead of the train (e.g., called a safety zone (SZ) or gabarit) with a detection probability (PD) of the obstacle above a predetermined threshold and a false alarm rate (FAR) below a second predetermined threshold. Summary of the Invention

[0004] One aspect of the present invention may provide a system for increasing the sampling rate of an imager detector for a selected region of interest, the system including an imaging device and a processing unit in communication with the imaging device, the imaging device configured to acquire a plurality of data sets for a corresponding plurality of image frames by performing a corresponding plurality of image frame processing cycles, the processing unit configured to define a special region of interest (SROI) in each of at least some of the plurality of image frames based on the data sets of the respective image frames, and the imaging device further configured to acquire at least one partial data set of the SROI during each of at least some of the plurality of image frame processing cycles and within a residual time between an end of an image frame acquisition time and an end of the respective image frame processing cycle. Another aspect of the disclosure may provide a method for increasing an imager detector sampling rate for a selected region of interest, the method including: acquiring, by an imaging device, a plurality of data sets for a corresponding plurality of image frames by performing a corresponding plurality of image frame processing cycles; defining, by a processing unit, a special region of interest (SROI) in each of at least some of the plurality of image frames based on the data sets of the respective image frames; and acquiring, by the imaging device, at least one partial data set of the SROI during each of at least some of the plurality of image frame processing cycles and within a residual time between an end of an image frame acquisition time and an end of an image frame processing cycle. These, additional, and / or other aspects and / or advantages of the present invention will be set forth in the following detailed description, or may be inferred from the detailed description, and / or learned by practicing the invention. For a better understanding of embodiments of the present invention and to show how embodiments of the present invention may be practiced, reference is made, by way of example only, to the accompanying drawings, in which like numerals indicate corresponding elements or sections throughout. [Brief explanation of the drawings]

[0005] [Figure 1A] 1 is a schematic diagram of an image frame depicting a rail with a safe braking line defining a safe braking distance range, according to some embodiments of the present invention; FIG. [Figure 1B] 1 is a schematic diagram of an image frame depicting a rail and a region of particular interest within the image frame, according to some embodiments of the present invention; [Figure 2] 1 is a schematic time graph of typical image frame processing by an imaging device; [Figure 3] 4 is a time graph of image frame processing according to an embodiment of the present invention. [Figure 4] 1 is a schematic diagram of a system for increasing the sampling rate of an image detector for a selected region of interest within an image frame, in accordance with some embodiments of the present invention. [Figure 5] 1 is a flowchart of a method for increasing the sampling rate of an image detector for a selected region of interest within an image frame, according to some embodiments of the present invention. [Figure 6] FIG. 1 is a schematic diagram of an optical system for obstacle detection by a moving train that can increase the sampling rate of an image detector for a selected region of interest within an image frame, in accordance with some embodiments of the present invention. [Figure 7-1] 1 is a flowchart of a method for obstacle detection by a moving train that increases the sampling rate of an image detector for a selected region of interest within an image frame, in accordance with some embodiments of the present invention. It will be understood that for simplicity and clarity of illustration, elements shown in the figures have not necessarily been drawn to scale. For example, the dimensions of some of the elements may be exaggerated relative to other elements for clarity. Furthermore, where considered appropriate, reference numerals may be repeated among the figures to indicate corresponding or analogous elements. [Figure 7-2]1 is a flowchart of a method for obstacle detection by a moving train that increases the sampling rate of an image detector for a selected region of interest within an image frame, in accordance with some embodiments of the present invention. It will be understood that for simplicity and clarity of illustration, elements shown in the figures have not necessarily been drawn to scale. For example, the dimensions of some of the elements may be exaggerated relative to other elements for clarity. Furthermore, where considered appropriate, reference numerals may be repeated among the figures to indicate corresponding or analogous elements. DETAILED DESCRIPTION OF THE INVENTION

[0006] In the following description, various aspects of the present invention are described. For purposes of explanation, specific configurations and descriptions are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to those skilled in the art that the present invention can be practiced without the specific details set forth herein. Furthermore, well-known features may be omitted or simplified so as not to obscure the present invention. With particular reference to the drawings, the details shown are presented by way of example only for the purpose of illustrative discussion of the present invention and to provide what is believed to be the most useful and readily understood of the principles and conceptual aspects of the present invention. In this regard, no attempt has been made to go into more structural detail of the present invention than is necessary for a fundamental understanding of the present invention; the description taken in conjunction with the drawings will make it apparent to those skilled in the art how several forms of the present invention may be embodied in practice.

[0007] Before at least one embodiment of the invention is described in detail, it is to be understood that the invention is not limited in its application to the details of construction and the arrangement of components set forth in the following description or illustrated in the drawings. The invention is applicable to other embodiments and combinations of the disclosed embodiments, which can be practiced or carried out in various ways. Also, it is to be understood that the phraseology and terminology employed herein is for the purpose of description and should not be regarded as limiting.

[0008] As will become apparent from the description that follows, unless specifically stated otherwise, statements in the specification utilizing terms such as "processing," "computing," "calculating," "determining," "enhancing," etc. will be understood to refer to the actions and / or processes of a computer or computing system that manipulate and / or transform data represented as physical quantities, such as quantities in electronics, registers, and / or memory of a computing system, into other data similarly represented as physical quantities in the computing system's memory, registers, or such information storage, transmission, or display device. Any of the disclosed modules or units may be implemented, at least in part, by a computer processor.

[0009] Some aspects of this disclosure may provide systems and methods for increasing the sampling rate of an imaging device for a selected region of interest within an image frame. According to some embodiments, the system may include an imaging device and a processing unit.

[0010] According to some embodiments, the imaging device can be configured to acquire a plurality of data sets for a corresponding plurality of image frames by performing a corresponding plurality of image frame processing cycles. According to some embodiments, the processing unit can be configured to define a particular region of interest in each of at least some of the plurality of image frames acquired by the imaging device based on the respective image frame data sets. The SROI can be a region within an image frame that may require an extended image processing area (e.g., spatial resolution).

[0011] According to some embodiments, the imaging device can be further configured to acquire at least one partial data set of the SROI during at least some of each of the plurality of image frame processing cycles and within a residual time between the end of the image frame acquisition time and the end of the respective image frame processing cycle. Advantageously, the disclosed systems and methods can enable an increased rate of acquiring data sets of the SROI within full image frames while maintaining the frame rate of the imaging device at a predetermined frame rate value.

[0012] 1A, a schematic diagram of a rail 110 with side margins 120 and a safety braking line 142 defining a safe braking distance range 140 is shown, in accordance with some embodiments of the present invention. Also, referring to FIG. 1B, a schematic diagram of image frames 100a, 100b depicting the rail 110 and a specific region of interest (SROI) 180 within the image frames is shown, in accordance with some embodiments of the present invention.

[0013] A moving train's safety zone 160 (e.g., depicted in FIG. 1A by a light gray color) may be defined as an area with a defined margin 120 on either side of the rail 110 from the train's leading edge (e.g., the train's locomotive) to a safe braking distance 140 along the rail 110 ahead of the train. The safety zone 160 may represent an area where identified objects are likely to pose a hazard to the moving train.

[0014] Typically, the safety zone 160 may have a shape in the image frame 100 that narrows from the bottom of the image area near the bottom of the image frame 100 as the safety zone 160 progresses towards the top of the image frame 20. The safe braking distance 140 may be directly proportional to the speed at which the train is moving (and, to a lesser extent, the mechanical and weather conditions of the train and rails).

[0015] A horizontal line 144 drawn a distance from the safety brake line 142 (towards the moving train) in FIG. 1A may define a specific region of interest (SROI) within the safety zone 160, and due to its distance from the train, extended processing resolution may be required to ensure sufficient ability to identify objects that may pose a threat to the train.

[0016] For example, SROI180 is a square with a width of X SROI And the height is Y SROI and has a rectangular shape with dimension X SROI is the horizontal dimension of the image frame 100 x frame is parallel to the dimension Y SROI is the vertical dimension Y of the image frame 100 frame The location of the SROI 180 within the image frame 100 can be indicated by the two-dimensional distance of one of the corners from a reference corner of the image frame 100. For example, the location of the SROI 180 within the image frame 100 can be determined by the horizontal distance X 180 and the vertical distance Y 180 It can be shown by:

[0017] The size, aspect ratio, and location (collectively SROI parameters) of the SROI 180 within the image frame 100 can be determined or selected, for example, so that the SROI 180 encompasses the distal end of the safety zone 160. The size of the SROI 180 can be set to balance the need to provide as high a resolution as possible for details within the SROI 180 with the need to operate within predetermined performance figures for the system. A rectangular shape of the SROI 180, for example, can be preferred for systems that support direct, easy, and resource-saving setting of the location and size of the SROI 180.

[0018] Determining / defining the parameters of SROI 180 may depend on one or more of the following considerations: (i) desired object resolution in the SROI, (ii) expected or desired probability of detection and false alarm rate, (iii) available computational resources for image processing, (iv) available frame rate of the imaging device, etc. For example, the vertical dimension and vertical position of SROI 180 may be selected to encompass safety braking line 142 and horizon 144. The horizontal dimension and horizontal position of SROI 180 may be selected to encompass the entire safety zone 160 extending between safety braking line 142 and horizon 144. According to some embodiments, SROI 180 may be defined in the image frame using a tracking module (e.g., as described below with respect to FIG. 6).

[0019] The tracking module can be configured to define and track locations within the image frames where the rail 110 is imaged. The tracking module can be further configured to define locations of the rail 110 within subsequent image frames 100, thereby tracking the location of the SROI 180 within the image frames 100. For example, FIG. 1B depicts a first image frame 100a having an SROI 180 located around a distal end of the rail 110 substantially at the center of the first image frame 100a and a second image frame 100 having an SROI 180 located around a distal end of the rail 110 lateral to the center of the second image frame 100, as a result of operation of the tracking module.

[0020] One way to reach a high probability of detection of obstacles that may threaten the train and / or a low false alarm rate is to reduce the probability of an event by choosing an SROI 180 that is smaller than the entire image frame 100. The drawback of this is that events outside the SROI 180 will not be detected, and some of them may be too important to be falsely detected.

[0021] Another way to reach a high probability of detecting obstacles that may threaten the train and / or a low false alarm rate is to increase the sampling bandwidth (BW) by increasing the frame rate of the imaging device, which may have the consequence of increasing the load on the computational resources (e.g., processing unit) of the system.

[0022] According to some embodiments, the disclosed systems and methods may enable increasing the sampling rate of SROI 180 within a complete image frame while maintaining the frame rate of the imaging device at a predetermined frame rate (e.g., as described below with respect to FIG. 3).

[0023] In this manner, the disclosed systems and methods may, for example, allow for an increased probability of detection of obstacles that may threaten a train and / or reduce the false alarm rate without substantially loading computational resources and allowing the use of existing interfaces of the imaging device.

[0024] Referring to Figure 2, a schematic time graph 200 of typical image frame processing by an imaging device is shown. An image frame is generally referred to as an image frame (e.g., interchangeably referred to herein as "t cyc The images are acquired at a predetermined frame rate (hereinafter interchangeably referred to as "FR") having a predetermined cycle time 220 between the predetermined frame rates (hereinafter interchangeably referred to as "FR"), where the predetermined cycle time 220 is inversely proportional to the predetermined frame rate (e.g., t cyc = 1 / FR). In general, the acquisition of each image frame is performed over the image frame acquisition time (e.g., here interchangeably referred to as “Δt at ") and includes the acquisition of a data item (e.g., a data set) according to the maximum data capacity (DCM) 260 per time unit (e.g., pixels / time) of the imaging device. Thus, in normal mode operation of the imaging device, each Δt atThe amount of data items acquired at a given frame rate (FR) of the imaging device (e.g., interchangeably referred to herein as "pixels per frame" or "PPF") can be expressed by Equation 1, and the amount of data items acquired per second at a given frame rate (FR) of the imaging device (e.g., interchangeably referred to herein as "DPS") can be expressed by Equation 2. PPF=Δt ac ·DCM (Formula 1) DPS=PF*FR=Δt*DCM*FR (Equation 2)

[0025] A typical imaging device may have a certain maximum data processing capability, including the accumulation of image photons in the imager, image data transfer from the imaging device, image data saving, and image data processing. The specific capabilities of an imaging device depend on the image frame acquisition time 240 (Δt at ) can be defined. Generally, the image frame acquisition time 240 (Δt at ) is the predetermined cycle time 220 (t cyc ) which is smaller than each predetermined cycle time 220 (e.g., t cyc ) with remaining time 280 (here interchangeably referred to as "t res This is due to the existence of a "

[0026] 3, a time graph 300 of image frame processing is shown, in accordance with an embodiment of the present invention. An image frame processing cycle occurs over a predetermined cycle time 320 (e.g., t cyc ) during which a full image frame of data items (e.g., data set) is acquired. at )and, imaging device is busy Remaining Remaining time 380 (e.g., t res For example, predetermined cycle time 320, image frame acquisition time 340, and residual time 380 may be similar to predetermined cycle time 220, image frame acquisition time 240, and residual time 280, respectively, described above with respect to FIG.

[0027] According to an embodiment, during the remainder time 380 of at least one image frame processing cycle, at least one additional cycle may be performed to acquire data items for selected portions of the image frames (e.g., as shown in FIG. 3). Data items acquired from selected portions of the image frames may be referred to herein interchangeably as "partial data items," or "partial data sets," or "partial data sets." Acquisition of partial data items / partial data sets for selected portions of the image frames may include:

[0028] The partial acquisition time 390 (herein referred to interchangeably as "Δt pat ”) may follow. The selected portion of the image frame may be an area within the image frame where enhanced image processing resolution may be required. The selected portion of the image frame may be, for example, a particular region of interest within the image frame, such as the SROI 180 described above with respect to FIGS. 1A and 1B. The image portion acquisition time 390 (Δt pat ) can depend, for example, on the size of the selected portion and the acquisition data rate (pixels / ms). Assuming that the acquisition data rate of the selected portion is the same as the acquisition data rate of the full image frame acquisition, the ratio Δt pda / Δt da is equal to the ratio of the area of the selected portion of the image frame to the area of the full image. In some embodiments, the selected portion of the image frame is selected based on the area of the selected portion of the image frame (e.g., as shown in FIG. 3). pda <<Δt da For example, the selected portion of the image frame may be 200x200 pixels compared to a full image frame having 1024x720 pixels. In this example, the fractional amount of data items obtained from the selected portion of the image frame may be only 5% of the amount of data items that would need to be obtained from the full image frame.

[0029] Thus, one or more additional cycles of acquiring partial data items / partial data sets of selected portions of the image frame can be performed during the remaining time 380 of each of one or more image frame processing cycles, thereby increasing the image resolution of details of selected portions of the image frame without changing the frame rate or needing to exceed a predetermined maximum data capacity (DCM) 360 of the imaging device (such as DCM 260 described above with respect to FIG. 2).

[0030] For example, in the embodiment shown in FIG. 3, the amount of data items per second (DPS) acquired at a given frame rate (FR) of the imaging device can be expressed by Equation 3: DPS=(Δt da +Δt pda )·DCM·FR|Δt da >>Δt pda ≒Δt da DCM FR (Equation 3)

[0031] 4, a schematic diagram of a system 400 for increasing the sampling rate of an imager detector of a selected region of interest of an image frame is shown, in accordance with some embodiments of the present invention. According to some embodiments, the system 400 may include an imaging device 410 and a processing unit 420. The system 400 may be located in a train locomotive such that the imaging device 410 faces in the direction of train travel. However, the system 400 may be applied to other applications (e.g., automobiles, etc.) as well.

[0032] According to some embodiments, the imaging device 410 can be configured to acquire a plurality of data sets of corresponding image frames by performing a corresponding plurality of image frame processing cycles. For example, the image frames acquired by the imaging device 410 can be similar to the image frames 100 described above with respect to FIG. 1A.

[0033] According to some embodiments, the processing unit 420 can be configured to define a specific region of interest (SROI) for each of at least some of the image frames acquired by the imaging device 410 based on the dataset of the respective image frames. The SROI can be a region within the image frame where enhanced image processing resolution may be required. For example, the SROI can be the SROI 180 described above with respect to FIGS. 1A and 1B.

[0034] According to some embodiments, the imaging device 410 may be further configured to acquire at least one partial data set of the SROI during each of at least some of the multiple image frame processing cycles, within the remaining time between the end of the image frame acquisition time and the end of the respective image frame processing cycle (e.g., as described above with respect to FIG. 3).

[0035] Referring to FIG. 5, a flowchart of a method 500 for increasing the sampling rate of an imager detector for a selected region of interest within an image frame is shown, in accordance with some embodiments of the present invention. Method 500 may be implemented by system 400 (e.g., as described above with respect to FIG. 4) that may be configured to implement method 500. Method 500 is not limited to the flowchart shown in FIG. 5 and the corresponding description. According to some embodiments, method 500 may include acquiring, by an imaging device, a plurality of data sets of corresponding image frames by performing a corresponding plurality of image frame processing cycles (stage 510), such as imaging device 410 described above with respect to FIG. 4.

[0036] According to some embodiments, the method 500 may include defining a specific region of interest (SROI) for each of at least some of the plurality of image frames acquired by the imaging device based on a dataset of the respective image frames. For example, the SROI described above with respect to FIG.

[0037] According to some embodiments, the method 500 may include acquiring, by the imaging device, at least one partial data set of the SROI during at least some of the image frame processing cycles and within a remaining time between the end of the image frame acquisition time and the end of the respective image frame processing cycle (e.g., as described above with respect to FIG. 3). Advantageously, the system 400 and method 500 may increase the rate at which data sets of the SROI are acquired within full image frames while maintaining the frame rate of the imaging device at a predetermined frame rate.

[0038] 6, a schematic diagram of an optical system 600 for obstacle detection by a moving vehicle 90, such as a train, and capable of increasing the sampling rate of an imager detector of a selected region of interest within an image frame, is shown, in accordance with some embodiments of the present invention. According to some embodiments, the system 600 can include an imaging device 610 and a processing unit 620. The system 600 can be located on the locomotive 92 of the train 90 such that the imaging device 610 faces in the direction of travel of the train 90.

[0039] According to some embodiments, the imaging device 610 can be configured to acquire a plurality of data sets of corresponding image frames by performing a corresponding plurality of image frame processing cycles. For example, the image frames acquired by the imaging device 610 can be similar to the image frames 100 described above with respect to Figures 1A and 1B. In some embodiments, the imaging device 610 is an infrared detector.

[0040] The image frames may depict at least the rail 110 ahead of the moving locomotive 92. The image frame processing cycles may be performed by the imaging device 610 at a predetermined frame rate and with a predetermined cycle time between image frames. For example, the predetermined frame rate FR, predetermined cycle time 320 (e.g., t cyc) and an image frame processing cycle. According to some embodiments, the processing unit 620 may include a tracking module 622.

[0041] In some embodiments, the tracking module 622 can be configured to detect rails in each of at least some of the image frames captured by the imaging device 410. For example, the rails can be rails such as rails 110 described above with respect to FIG. 1A. The rails can be detected in the image frames using any technique known in the art. For example, the rails can be detected based on the temperature difference between the rails and their background (e.g., when the imaging device 610 is an infrared detector).

[0042] In some embodiments, the tracking module 622 can be configured to define a margin on either side of each detected rail for at least some of the multiple image frames. For example, the margin can be the margin 120 described above with respect to FIG. 1A. The margin can be defined according to the efficiency / quality of rail detection. For example, as rail detection improves, the distance from the margin to the rail can be shortened. Furthermore, in this example, if the rail is not well detected, the margin can be set at a larger distance from the rail to compensate for the poor rail detection.

[0043] In some embodiments, the tracking module 622 can be configured to define a safe braking line for each of at least some of the plurality of image frames based on a safe braking distance of the train 90. For example, the safe braking line and the safe braking distance can be similar to the safe braking line 142 and the safe braking distance 140 described above with reference to FIG. 1A. The safe braking distance can be determined based on, for example, the speed of the train 90.

[0044] In some embodiments, the tracking module 622 can be configured to define a safety zone for each of at least some of the plurality of image frames based on the defined margin and the defined safety braking line. For example, the safety zone can be the safety zone 160 described above with reference to FIG. 1A.

[0045] In some embodiments, the tracking module 622 can be configured to define a specific region of interest (SROI) for each of at least some of the plurality of image frames at a distal end of the defined safety zone, such as the SROI 180 described above with respect to FIG. 1A. The SROI can be a zone whose distance from the train 90 may require enhanced image processing resolution to ensure sufficient ability to detect objects that may pose a threat to the train 90.

[0046] In some embodiments, the tracking module 622 may be configured to define the SROI in subsequent image frames, thereby tracking the location of the SROI within the image frames (e.g., as described above with respect to FIG. 1B). According to some embodiments, the imaging device 610 may be further configured to acquire at least one partial data set of the SROI during at least some of each of the multiple image frame processing cycles and within the remaining time between the end of the image frame acquisition time and the respective image frame processing cycle (e.g., as described above with respect to FIG. 3).

[0047] According to some embodiments, the processing unit 620 may include an obstacle detection module 624. The obstacle detection module 624 may be configured to analyze a dataset of a full image frame and / or a partial dataset of an SROI within the full image frame and, based on the analysis, detect potential objects / obstacles on the rail 110 and / or within the defined SROI.

[0048] Referring to Figure 7, a flowchart 700 of a method for obstacle detection by a moving train that increases the sampling rate of an imager detector for a selected region of interest within an image frame is shown, in accordance with some embodiments of the present invention. Method 700 can be implemented by system 600, which can be configured to implement method 700. It should be noted that method 700 is not limited to the flowchart illustrated in Figure 7 and the corresponding description. For example, in various embodiments, method 700 need not go through each of the illustrated boxes or stages, or in the exact order illustrated and described.

[0049] According to some embodiments, method 700 may include acquiring, by an imaging device, a plurality of data sets of a corresponding plurality of image frames by performing a corresponding plurality of image frame processing cycles (stage 710). For example, the imaging device may be similar to imaging device 610 described above with reference to FIG. 6. According to some embodiments, method 700 may include defining, by a tracking module of the processing unit, a specific region of interest (SROI) in each of at least some of the plurality of image frames acquired by the imaging device based on the data sets of the respective image frames (stage 720). For example, the tracking unit and processing unit may be similar to tracking unit 622 and processing unit 620 described above with reference to FIG. 6. The SROI may be similar to SROI 180 described above with reference to FIGS. 1A and 1B. In some embodiments, method 700 may further include detecting rails in each of at least some of the plurality of image frames (stage 721) (e.g., as described with reference to FIG. 6).

[0050] In some embodiments, method 700 may further include defining margins on either side of the detected rail in each of at least some of the plurality of image frames (stage 722) (as described with reference to FIG. 6). In some embodiments, method 700 may further include defining a safe braking line in each of at least some of the plurality of image frames based on a safe braking distance of the train (as described above with reference to FIG. 6) (stage 723). In some embodiments, method 700 may include defining a safety zone in each of at least some of the plurality of image frames based on the defined margin and the defined safe braking line (e.g., as described above with reference to FIG. 6) (stage 724).

[0051] In some embodiments, method 700 may further include defining a specific region of interest (SROI) in each of at least some of the plurality of image frames within the defined safety zone (stage 725) (e.g., as described with reference to FIG. 6). In some embodiments, method 700 may further include defining the SROI in subsequent image frames (e.g., as described with reference to FIG. 6) thereby tracking the location of the SROI within the image frames (stage 726). According to some embodiments, method 700 may include acquiring, by the imaging device (e.g., as described with reference to FIGS. 3 and 6) at least one partial data set of the SROI during each of at least some of the plurality of image frame processing cycles, within a residual time between the end of the image frame acquisition time and the end of the respective image frame processing cycle (stage 730).

[0052] According to some embodiments, method 700 may include analyzing, by an obstacle detection module of the processing unit, the dataset of the full image frame and / or the partial dataset of the SROI within the full image frame, and based on the analysis, detecting potential objects / obstacles on the rail and / or within the defined SROI (stage 740), for example, an obstacle detection module such as obstacle detection module 624 described above with respect to FIG.

[0053] Advantageously, system 600 and method 700 can increase the sampling rate of SROI 180 within a full image frame while maintaining the frame rate of the imaging device at a predetermined frame rate (e.g., as described with respect to FIG. 3). In this manner, system 600 and method 700 can increase the probability of detecting obstacles that may threaten the train and / or reduce the false alarm rate without substantially loading computational resources and without enabling the use of existing interfaces of the imaging device.

[0054] According to some embodiments described above, higher resolution of a selected region of an image frame can be obtained without changing the predetermined frame rate or data capacity of the imaging device. The size and location of the selected portion within the image frame can be determined or indicated. According to some embodiments, the size and location of the selected portion within the image frame can be set to satisfy a specific region of interest (SROI) that requires higher image resolution.

[0055] For example, in a system usable for monitoring train tracks and providing advance warning of obstacles on or near the rails, increased image resolution may be required for a portion of the image that includes the distal end of the rail detected within the image frame (as described above with respect to FIGS. 1A and 1B, 6, and 7). A tracking module can be used to determine the location and size of the SROI. The tracking module can be a graphics processing unit that tracks the presence of the rail within the image frame. Such a tracking module can be embodied as a program executed on a computer that performs image processing. For example, if the proximal end of the rail within the image frame (typically near the center of the bottom edge of the image and prominently present) is tracked toward the top of the image frame, the distal end of the rail within the image frame can be detected with a relatively low additional computational load. The results of tracking the distal end of the train rail within the image frame can then be converted into the location and size of the SROI.

[0056] Aspects of the present invention are described above with reference to flowchart representations and / or sub-views of methods, apparatus (systems) and computer program products according to embodiments of the present invention. It will be understood that each portion and / or sub-view of the flowchart representations, and combinations of portions and / or sub-views of the flowchart representations, can be implemented by computer program instructions.

[0057] Computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, and the instructions, executed by the processor of the computer or other programmable data processing apparatus, can produce means for implementing the functions / acts specified in the flowcharts and / or sub-diagrams or portions. These computer program instructions can be stored on a computer-readable medium that can direct a computer, other programmable data processing apparatus, or other device to function in a particular way, and the instructions stored on the computer-readable medium create an article of manufacture containing instructions that implement the functions / acts specified in the flowcharts and / or sub-diagrams or portions thereof.

[0058] The computer program instructions may also be loaded into a computer, programmable data processing apparatus, or other device to cause the computer, other programmable apparatus, or other device to perform a series of operational steps, providing a process whereby the instructions executing on the computer or other programmable apparatus implement the functions / acts specified in one or more portions of the flowcharts and / or sub-diagrams.

[0059] The flowcharts and figures described above illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer programs according to various embodiments of this disclosure. In this regard, each portion within a flowchart or sub-diagram may represent a module, segment, or portion of code, including one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions shown in the portions may occur out of the order shown in the figures. For example, two portions shown in succession may in fact be executed substantially simultaneously, or the portions may be executed in the reverse order. It should be noted that each portion of the sub-diagrams and / or flowchart representations, and combinations of portions of the sub-diagrams and / or flowchart representations, may be implemented by a special-purpose hardware-based system that performs the specified functions or acts, or a combination of special-purpose hardware and computer instructions.

[0060] In the above description, one embodiment is an example or implementation of the invention. The various expressions "one embodiment," "an embodiment," "an embodiment," or "some embodiments" do not necessarily all refer to the same embodiment. Although various features of the invention may be described in the context of one embodiment, these features may also be provided separately or in any suitable combination. Conversely, although the invention may be described herein in the context of separate embodiments for clarity, the invention may also be implemented in a single embodiment. An embodiment of the invention may include features from different embodiments described above, and an embodiment may incorporate elements from other embodiments described above. The disclosure of elements of the invention in the context of a particular embodiment should not be construed as limited to use in only that particular embodiment. Furthermore, the invention can be practiced or implemented in various ways, and it should be understood that the invention may be implemented in an embodiment other than the embodiments described above.

[0061] The present invention is not limited to these diagrams or the corresponding descriptions. For example, the flow need not pass through each illustrated box or state, or in the exact same order as illustrated and described. The meanings of technical and scientific terms used herein, unless otherwise defined, should be generally understood by those skilled in the art to which the present invention pertains. While the present invention has been described with respect to a limited number of embodiments, these should not be construed as limiting the scope of the invention, but rather as some illustrations of preferred embodiments. Other possible variations, modifications, and applications are also within the scope of the present invention. Therefore, the scope of the present invention should not be limited to what has been described above, but rather by the appended claims and their legal equivalents.

Claims

1. 1. A system for increasing the sampling rate of an imager detector of a selected region of interest, comprising: An imaging device; a processing unit in communication with the imaging device; the imaging device is configured to acquire a plurality of data sets of a corresponding plurality of image frames by performing a corresponding plurality of image frame processing cycles; the processing unit is configured to define a specific region of interest (SROI) in each of at least some of the plurality of image frames based on the data set of each image frame of the plurality of image frames; the imaging device is further configured to acquire one partial data set of the SROI only during a residual time between an end of an image frame acquisition time and an end of the respective image frame processing cycle during at least some of the plurality of image frame processing cycles, during which the imaging device is not busy, each of the partial data sets being smaller than each of the data sets; the processing unit includes a tracking module configured to define and track a position of the SROI between acquisitions of a plurality of the image frames; The tracking module further comprises: detecting rails in each of at least some of the plurality of image frames; defining margins on either side of the detected rail in each of at least some of the plurality of image frames, wherein the margins are adjusted in size according to a quality of detection of the detected rail; system.

2. the imaging device is disposed on a locomotive of the train so as to face the direction of travel of the train, and the tracking module further comprises: defining a safe braking line in each of at least some of the plurality of image frames based on a safe braking distance of the train; defining a safety zone in each of at least some of the plurality of image frames based on the defined margin and the defined safety braking line; defining the SROI in each of at least some of the plurality of image frames at a distal end of the defined safety zone; The system of claim 1 configured to:

3. The processing unit analyzing at least the partial data set of the SROI within a full image frame; Detecting potential objects / obstacles on the rail or within the defined SROI based on said analysis; 3. The system of claim 2, comprising an obstacle detection module configured to:

4. 1. A method for increasing a sampling rate of an imager detector for a selected region of interest, comprising: acquiring, with an imaging device, a plurality of data sets of a corresponding plurality of image frames by performing a corresponding plurality of image frame processing cycles; defining, by a processing unit, a specific region of interest (SROI) in each of at least some of the plurality of image frames based on the data set for each image frame of the plurality of image frames; acquiring, with the imaging device, one partial data set of the SROI during each of at least some of the plurality of image frame processing cycles, only within a residual time between an end of an image frame acquisition time and an end of the respective image frame processing cycle, during which the imaging device is not busy; each of the partial data sets is smaller than each of the data sets; a tracking module defining and tracking the position of the SRIOI between acquisitions of a plurality of the image frames; The tracking module further detecting rails in each of at least some of the plurality of image frames; defining margins on either side of the detected rail in each of at least some of the plurality of image frames, wherein the margins are adjusted in size according to a quality of detection of the detected rail; method.

5. A step of defining, by the tracking module, a safe braking line in each of at least some of the plurality of image frames based on a safe braking distance of the train; defining, by the tracking module, a safety zone in each of at least some of the plurality of image frames based on the defined margin and the defined safety braking line; defining, by the tracking module, the SROI in each of at least some of the plurality of image frames at a distal end of the defined safety zone; The method of claim 4 further comprising:

6. analyzing, by an obstacle detection module of the processing unit, at least the partial data set of the SROI within a full image frame; 6. The method of claim 5, further comprising: detecting, by the obstacle detection module, potential objects / obstacles on the rail or within the defined SROI based on the analysis.

Images