GB2615107A

GB2615107A - System and apparatus suitable for sign recognition and/or restoration thereof, and processing method in association thereto

Info

Publication number: GB2615107A
Application number: GB2201093.8A
Authority: GB
Inventors: Dhiman Ashish; Reddy Deepak; Bhat Prashant; Ponkumar Senthil
Original assignee: Continental Autonomous Mobility Germany GmbH
Current assignee: Continental Autonomous Mobility Germany GmbH
Priority date: 2022-01-28
Filing date: 2022-01-28
Publication date: 2023-08-02
Also published as: GB202201093D0

Abstract

Recognition of faded, worm, obstructed or graffitied signs, comprising: a first module 202 that receives an input signal comprising a data signal, corresponding to an image of a sign, and a reference signal, corresponding to known sign data; and a second module 204 that outputs a classification of whether the sign is a faded, worm, obstructed or graffitied sign or an irrelevant (unknown) sign. The sign may be a road traffic sign. When the sign is determined to be faded, worm, obstructed or graffitied, the second module may perform an in-painting restoration technique to fill in any missing information based on neighbourhood segment information. The resulting enhanced image may be displayed to a vehicle’s user or classified.

Description

SYSTEM AND APPARATUS SUITABLE FOR SIGN RECOGNITION AND/OR RESTORATION THEREOF, AND A PROCESSING METHOD IN ASSOCIATION

THERETO

Field Of Invention

The present disclosure generally relates to one or both of a system and an apparatus suitable for recognizing one or more signs such as, for example, traffic sign(s). More specifically, the present disclosure relates to a system and/or an apparatus suitable for recognition of one or more disabled signs (e.g., disabled traffic signs). The present disclosure further relates a processing method associable to the system and/or the apparatus.

Background

Generally, traffic signs are important for road use. For example, traffic signs can convey essential information to a road user (e.g., a driver operating a vehicle and/or an autonomous vehicle). Such essential information can include, for example, speed limits, directions, possible road conditions ahead (e.g., existence of speed regulating humps ahead and/or pedestrian crossing ahead) and/or general information concerning a location (e.g., name of a location) etc. A/ben a traffic sign cannot be perceived properly, there is possibility of error(s) in perception of a traffic sign. For example, the speed limit associated with a road may not be perceived properly leading to a possibility that the speed limit perceived On error) is higher than what it ought to be.

Appreciably, such error(s) in perception can potentially compromise road safety (e.g., an autonomous vehicle and/or a driver may exceed speed limit unintentionally). Moreover, such error(s) in perception can, for example, potentially compromise operational reliability of an autonomous vehicle (e.g., name of a location may be perceived erroneously, potentially causing errors in navigation).

The present disclosure contemplates that there is a need to address the aforementioned possibility of perception error(s).

Summary of the Invention

In accordance with an aspect of the disclosure, there is provided an apparatus which can, for example, be suitable for use for recognition of a disabled sign (e.g., a disabled traffic sign). The apparatus can include a first module and a second module. The first module can be coupled to the second module.

The first module can be configured to receive at least one input signal which can include at least one data signal and at least one reference signal.

The second module can be configured to produce at least one output signal based on the data signal(s) and the reference signal(s). The data signal(s) can correspond to at least one read symbol which can be indicative of a spurious sign. The spurious sign can be associated with either a disabled sign or an actual false positive sign. The output signal(s) can, in one embodiment, be indicative of whether the spurious sign is a disabled sign or otherwise (i.e., not a disabled sign such as an actual false positive sign).

In one embodiment, when the spurious sign is a disabled sign, the second module can be configured to perform restoration-based processing such that a true sign can be recovered from a disabled sign. The restoration-based processing can, for example, be associated with at least one in-painting technique. In one example, the in-painting technique can facilitate information processing by manner of filling in missing information based on neighborhood segment information.

Moreover, in one embodiment, the second module can be configured to classify the true sign.

The present disclosure contemplates that it would be helpful to facilitate recognition of a disabled sign. In one embodiment, recognition of a disabled sign can, for example, be associated with restoring readability of information (i.e., which readability had been adversely affected) so that information intended to be conveyed can be properly perceived (e.g., by a driver and/or an autonomous vehicle).

It is appreciable that, by doing so, road safety (e.g., speed limits can be properly perceived by a driver) and/or operational reliability (of, for example, an autonomous vehicle) can possibly be improved. It is contemplated that by recognizing the disabled sign(s) and, optionally, restoring readability of information (i.e., which readability had been adversely affected) so that information intended to be conveyed can be properly perceived (e.g., by a driver and/or an autonomous vehicle), the possibility of unintended (e.g., unintended speed) operation of a vehicle can at least be reduced or, preferably, eliminated.

The above-described advantageous aspect(s) of the apparatus of the present disclosure can also apply analogously (all) the aspect(s) of a below described processing method of the present disclosure. Likewise, all below described advantageous aspect(s) of the processing method of the disclosure can also apply analogously (all) the aspect(s) of above described apparatus of the disclosure.

In accordance with another aspect of the disclosure, there is provided a processing method which can be usable for recognizing a disabled sign and/or restoration of a disabled sign.

The processing method can include a receiving step and a processing step.

The receiving step can include receiving (e.g., by the first module of the aforementioned apparatus) at least one input signal which can include at least one data signal and at least one reference signal.

The processing step can include processing (e.g., by the second module of the aforementioned apparatus) the received data signal(s) and the reference signal(s) to generate at least one output signal.

The data signal(s) can correspond to at least one read symbol which can be indicative of a spurious sign. The spurious sign can be associated with either a disabled sign or an actual false positive sign.

S

The output signal(s) can be indicative of whether the spurious sign is a disabled sign or otherwise (i.e., not a disabled sign such as an actual false positive sign).

In one embodiment, the processing step can further include a restoration step. In regard to the restoration step, when the spurious sign is a disabled sign, restoration-based processing can be performed (e.g., by the second module of the aforementioned apparatus) to recover a true sign from the disabled sign. Restoration-based processing can, for example, be associated with at least one in-painting technique. It is contemplated that the in-painting technique can be capable of facilitating information processing by manner of, for example, filling in missing information based on neighborhood segment information.

In one embodiment, the processing step can further include a classification step. In regard to the classification step, classification-based processing can be performed to classify the true sign.

The present disclosure further contemplates a computer program (not shown) which can include instructions which, when the program is executed by a computer (not shown), cause the computer to carry out any one of, or any combination of, the receiving step, the processing step and the output generating step, as discussed with reference to the processing method.

The present disclosure yet further contemplates a computer readable storage medium (not shown) having data stored therein representing software executable by 30 a computer (not shown), the software including instructions, when executed by the computer, to carry out any one of, or any combination of, the receiving step, the processing step and the output generating step, as discussed with reference to the processing method.

As mentioned earlier, the present disclosure contemplates that it would be helpful to facilitate recognition of a disabled sign. In one embodiment, recognition of a disabled sign can, for example, be associated with restoring readability of information (i.e., which readability had been adversely affected) so that information intended to be conveyed can be properly perceived (e.g., by a driver and/or an autonomous vehicle).

Brief Description of the Drawings

Embodiments of the disclosure are described hereinafter with reference to the following drawings, in which: Fig. 1 shows a system which can include at least one apparatus, according to an

embodiment of the disclosure;

Fig, 2 shows the apparatus of Fig, 1 in further detail, according to an embodiment of

the disclosure; and

Fig. 3 shows a processing method in association with the system of Fig. 1, according to an embodiment of the disclosure

Detailed Description

The present disclosure contemplates that there could be one or more errors in perceiving, for example, a sign (e.g., a traffic sign) if that sign is disabled. It is contemplated that a sign can be considered to be disabled if readability of information intended to be conveyed by the sign becomes adversely affected. In one example, readability of a sign can become impaired in a situation where information becomes obscured by graffiti. In another example, readability of a sign can become impaired because of discoloring etc. due to, for example, the sign being subjected to prolonged harsh weather conditions (e.g., prolonged exposure to harsh sunlight).

The present disclosure contemplates that it would be helpful to facilitate recognition of a disabled sign (e.g., a disabled traffic sign and/or a disabled road sign). Recognition of a disabled sign can, for example, be associated with determining whether a sign is disabled (or not). Recognition of a disabled sign can further, for example, be associated with restoring readability of information (i.e., which readability had been adversely affected) associated with a disabled sign so that information intended to be conveyed can be properly perceived (e.g., by a driver and/or an autonomous vehicle).

Appreciably, by doing so, road safety (e.g., speed limits can be properly perceived by a driver) and/or operational reliability (of, for example, an autonomous vehicle) can possibly be improved.

The foregoing will be discussed in further detail with reference to Fig. 1 to Fig. 3 hereinafter.

Referring to Fig 1, a system 100 is shown, according to an embodiment of the disclosure. The system 100 can be suitable for/be associated with recognition of one or more signs. Specifically, the system 100 can be suitable for/be associated with recognition of one or more traffic signs. More specifically, the system 100 can be suitable for/be associated with recognition of one or more disabled traffic signs. In one embodiment, the system 100 can be suitable for/be associated with recognition of at least one disabled traffic sign (and/or at least one disabled road sign) and, optionally, facilitating the restoration of perception (e.g., visual perception) of the recognized disabled traffic sign(s) and/or road signal(s).

In one embodiment, the system 100 can, for example, correspond to an electronic-based system which can be at least partially carried (e.g., the system being installed) by a, for example, vehicle (not shown). In one example, the system 100 can be fully (i.e., the entire system 100) carried by a vehicle. In another example, one or more portions of the system 100 can be carried by a vehicle whereas another one or more portions of the system 100 can be carried outside of the vehicle (e.g., at least one portion of the system 100 is not carried by the vehicle).

The system 100 can, for example, include one or more apparatuses 102, at least one device 104 and a communication network 106, in accordance with an embodiment of the disclosure. In one embodiment, the system 100 can further include, as an option, one or more host devices (not shown).

The apparatus(es) 102 can be coupled to the device(s) 104. Specifically, the apparatus(es) 102 can, for example, be coupled to the device(s) 104 via the communication network 106. The host device(s) can, for example, be coupled to one or both of the apparatus(es) 102 and the device(s) 104. Specifically, the host device(s) can, for example, be coupled to the apparatus(es) 102 and/or the device(s) 104 via the communication network 106.

In one embodiment, the apparatus(es) 102 can be coupled to the communication 30 network 106 and the device(s) 104 can be coupled to the communication network 106. Moreover, in one embodiment, the host device(s) can be coupled to the communication network 106. Coupling can be by manner of one or both of wired coupling and wireless coupling The apparatus(es) 102 can, in general, be configured to communicate with the device(s) 104 via the communication network 106, according to an embodiment of the disclosure. The host device(s) can, in general, be configured to communicate with the apparatus(es) 102 and/or the device(s) 104 via the communication network 106, according to an embodiment of the disclosure.

The apparatus(es) 102 can, for example, correspond to one or more computers (e.g., an electronic device/module having computing capabilities such as an electronic mobile device which can be carried into a vehicle or an electronic module which can be installed in a vehicle). Generally, the apparatus(es) 102 can, in one embodiment, be configured to perform one or more processing tasks. As a general example, the apparatus(es) 102 can be configured to receive one or more input signals and process the input signal(s) in a manner so as to produce one or more output signals. The apparatus(es) 102 will be discussed later in further detail with reference to Fig. 2, according to an embodiment of the disclosure. The input signal(s) can, for example, be based on communication from one or both of the device(s) 104 and the host device(s), as will be discussed in further detail in the context of an example implementation, in accordance with an embodiment of the disclosure.

The device(s) 104 can, for example, correspond to/be representative of at least one Traffic Sign Assist (TSA) system. The TSA system can, for example, be carried by a vehicle and can be configured to monitor the road ahead on which the vehicle is moving in a continuous manner. Generally, monitoring can be facilitated by, for example, a detection device (e.g., a stereo camera module) which can be carried by the vehicle (e.g., fitted behind the windscreen of the vehicle) and can be configured to capture one or more images associated with one or more signs (e.g., traffic/road signs). Moreover, the TSA system can be configured to process one or more images detected by the detection device by manner of recognition-based processing techniques (e.g., recognition of the shape of a road sign, a traffic sign and/or a traffic signal light). It is contemplated that the device(s) 104 can be capable of reading one or more (more preferably, every) symbols (e.g., road symbols and/or traffic symbols) depicted by the sign(s). The read symbol(s) can, for example, be cross-referenced/cross-checked with/against information carried by, for example, the host device(s). In this regard, the device(s) 104 can be configured to perform one or more comparison-based processing for the purpose of, for example, crossreferencing/cross checking as discussed earlier. Based on the aforementioned cross-referencing/cross-checking, the read symbol(s) (e.g., symbols that have been read) can be verified to be either an actual sign of interest (i.e., an actual road sign/an actual traffic sign) and not a spurious sign (e.g., an advertisement related) which is not associated with providing actual traffic information/information concerning the road. As an option, the TSA system can be configured to display the corresponding road sign, road sign and/or traffic light in an instrument cluster of the vehicle and/or as well as on the map(s) in a navigation system. One or more data signals corresponding to, for example, read symbol(s) being indicative of a spurious sign can be communicated from the device(s) 104, in accordance with an embodiment of the disclosure.

The host device(s) (e.g., one or more computers or one or more databases) can, in one example, correspond to a traffic network database system which can be an online-based system which can be remote from the vehicle and/or a localized system (i.e., not connected online) carried by the vehicle, in accordance with an embodiment of the disclosure. In another example, the host device(s) can correspond to a navigation system associated with the vehicle, in accordance with an embodiment of the disclosure. Moreover, the host device(s) can be configured to carry a software and/or hardware platform which can be configured to perform one or more processing tasks which can, for example, include one or both of learning-based processing tasks (e.g., machine-learning based processing) and prediction-based processing. Furthermore, the host device(s) can carry a database of known and/or officially recognized signs (e.g., known/officially recognized traffic signs, road signs and/or traffic signal lights). One or more reference signals corresponding, for example, to/indicative of the known and/or officially recognized signs can be communicated from the host device(s), in accordance with an embodiment of the disclosure.

The communication network 106 can, for example, correspond to an Internet communication network, a wired-based communication network, a wireless-based communication network, or any combination thereof Communication 0.6., between the apparatus(es) 102, the device(s) 104 and the host device(s), or any combination thereof) via the communication network 106 can be by manner of one or both of wired communication and wireless communication.

Earlier mentioned, the apparatus(es) 102 can be configured to receive one or more input signals and process the input signal(s) in a manner so as to produce one or more output signals. The output signal(s) can, in one example, be one or both of visually perceivable and audibly perceivable (i.e., visually perceivable and/or audibly perceivable). The output signal(s) can, in another example, be communicated for further processing. The output signal(s) can, in yet another example, be visually and/or audibly perceivable, and be communicated for further processing. This will be discussed in further detail in the context of an example implementation hereinafter.

In the example implementation, the present disclosure contemplates that the input signal(s) (i.e., received by the apparatus(es) 102) can include one or both of the data signal(s) (i.e., communicated from the device(s) 104) and the reference signal(s) (i.e., communicated from the host device(s)). In a specific example, the input signal(s) can include the data signal(s) and the reference signal(s), in accordance with an

embodiment of the disclosure.

It is contemplated that the input signal(s) can be received by the apparatus(es) 102 and processed in a manner so as to distinguish whether a spurious sign is a disabled sign or otherwise. For example, the apparatus(es) 102 can be configured to perform verification-based processing to confirm whether a spurious sign is a disabled sign or not. Verification-based processing can, for example, be by manner of comparison. For example, comparison can be based on the data signal(s) and the reference signal(s). Earlier mentioned, the reference signal(s) can, for example, correspond to/ be indicative of the known and/or officially recognized signs. In this regard, a comparison can, for example, effectively be made as between a spurious sign and known and/or officially recognized sign(s). In this manner, the apparatus(es) 102 can, for example, be configured to recognize a disabled sign.

In an example, if, based on the comparison, it can be determined that a spurious sign and a known and/or officially recognized sign have notable areas/portions/regions of similarity (e.g., 25% or more of the areas/portions/regions being considered to be at least similar), a spurious sign can be identified as a disabled sign. Otherwise (e.g., less than 25% similarity), a spurious sign can be regarded as not a disabled sign and identified as an "actual false positive sign" (e.g., an advertisement sign which is not related to a traffic sign, road sign and/or traffic signal lights) in this regard.

Moreover, based on the comparison, the apparatus(es) 102 can be configured to perform classification-based processing, in accordance with an embodiment of the disclosure. In regard to classification-based processing, the apparatus(es) 102 can be configured to classify whether a received data signal can be associated of a disabled sign or otherwise. The apparatus(es)102 can, for example, be configured to generate and communicate one or more classification signals based on the aforementioned classification concerning whether a received data signal can be associated with a disabled sign or not. The classification signal(s) can, for example, be communicated from the apparatus(es) 102 for further processing. In one example, the classification sign(s) can be communicated to the host device(s) for learning based processing and/or prediction-based processing. It is contemplated that by manner of learning based on the classification signal(s), it is possible that prediction of whether future instances of received data signals can be associated with disabled signs (or not) can be facilitated. This may possibly facilitate in a more efficient processing (e.g., there is a possibility that detailed comparison may not be necessary or comparison may possibly be omitted) of such future received data signals and/or a more reliable identification 0.e., based on a combination of comparison and prediction) of whether such future received data signals can be associated with disabled signs (or not). In another example, the classification sign(s) can be communicated to one or both of an internal storage module (i.e., carried by the apparatus(es) 102) and an external storage module (i.e., remote from the apparatus(es) 102) for storage (e.g., storage-based processing), for future retrieval/access if desired.

Where a spurious sign can be determined to be a disabled sign, the apparatus(es) 102 can, as an option, be configured to further process the input signal(s) associated with the spurious sign (i.e., which can be determined to be a disabled sign) in a manner so as to facilitate restoration of the disabled sign so that the disabled sign can be intelligibly perceived (e.g., capable of being visually and/or audibly perceived in an intelligible manner), in accordance with an embodiment of the disclosure. Processing associated with restoration of a disabled sign can be referred to as restoration-based processing. Restoration-based processing can, for example, be associated with an in-painting based technique which can facilitate information processing by manner of, for example, filling in missing information (e.g., due to being obscured and/or caused by fading) based on neighborhood segment information. In this manner, it is contemplated that information intended to be conveyed can be possibly be restored and proper perception (e.g., by a driver and/or an autonomous vehicle) can possibly be facilitated.

It is contemplated that by manner of restoration as discussed above, a true sign can be recovered from a disabled sign. For example, a true sign which conveys original information intended to be conveyed can be restored from a disabled sign.

Therefore, it is appreciable that, generally, after a disabled sign is recognized (e.g., by the apparatus(es) 102), the disabled sign which is recognized can, optionally, be further processed (e.g., by manner of restoration-based processing) in a manner so that a true sign can be recovered from the disabled sign. In this manner, in accordance with an embodiment of the disclosure, recognition of a disabled sign can be associated with determining whether a sign is disabled (or not) and/or, as an option, be associated with restoring readability of information 0.e., which readability had been adversely affected) associated with a disabled sign so that information intended to be conveyed can be properly perceived (i.e., recovery of a true sign from a disabled sign).

Moreover, in the example implementation, the apparatus(es) 102 can be further configured to communicate one or more output signals which can, in one embodiment, correspond to/include/be associated with one or more true signs (i.e., restored from corresponding one or more disabled signs). In another embodiment, the output signal(s) can correspond to/include/be associated with an indication as to whether a received data signal can be associated with a disabled sign or not. In yet another embodiment, the output signal(s) can correspond to/include/be associated with the true sign(s) and an indication as to whether a received data signal can be associated with a disabled sign or not. In one example, the output signal(s) can include one or both of a first at least one output signal and a second at least one output signal (i.e., a first at least one output signal and/or a second at least one output signal). The first output signal(s) can, for example, correspond to/include/be associated with one or more true signs, in accordance with an embodiment of the disclosure. The second output signal(s) can, for example, correspond to/include/be associated with an indication as to whether a received data signal can be associated with a disabled sign or not.

In the above manner, the input signal(s) can be received by the apparatus(es) 102 and processed in a manner so as to generate the output signal(s).

The example implementation, as discussed above, will now be discussed in further detail based on an example scenario, in accordance with an embodiment of the disclosure.

In the example scenario, the device(s) 104 (e.g., corresponding to/be representative 30 of at least one TSA system) can include a traffic sign detection module which can be configured to detect one or more signs. The detected signs can be classified into different classification groups based on, for example, shapes (e.g., circular, triangular and rectangular etc.) of the detected signs. The device(s) 104 can, in this regard, include a classification module for classifying the detected signs, in accordance with an embodiment of the disclosure. The classification module can be configured to perform a first level classification (e.g., based on shapes of the detected signs), in accordance with an embodiment of the disclosure. The first level classification can include, for example, a first classification group, a second classification group and a third classification group, in accordance with an embodiment of the disclosure. The first classification group can, for example, be associated with circular signs. The second classification group can, for example, be associated with triangular signs. The third classification group can, for example, be associated with rectangular signs.

In the example scenario, the device(s) 104 can be configured to perform further processing based on one classification group (e.g., the first classification group which can, for example be associated with circular signs). It is contemplated that a circular sign can, for example, be potentially indicative of a speed limit or no entry. When a true positive sign can be determined by the device(s) 104 (e.g., by manner of recognition-based processing techniques), the device(s) 104 can, as an option, be further configured to process the first classification group by manner of further classification (e.g., classify speed limit signs and no-entry signs into separate groups) and communicate such information (i.e., based on the aforementioned further classification) to, for example, a TSA functionality.

Conversely, if a true positive sign cannot be determined by the device(s) 104, the device(s) 104 can be configured to preliminarily identify such a sign to be a garbage category sign (i.e., which can be associated with/include one or more garbage signs) and communicate this information for further processing to determine whether such a garbage sign is a disabled sign or an actual false positive sign (i.e., meaning such a sign is not a valid sign). Information (e.g., corresponding to the earlier mentioned data signal(s)) indicating that a sign could potentially be a garbage sign can, for example, be communicated for the device(s) 104 to the apparatus(es) 102 for processing.

As discussed earlier, per the example implementation, the apparatus(es) 102 can be configured to determine whether a received data signal can be associated of a disabled sign or otherwise. In the example scenario, the apparatus(es) 102 can be configured to determine whether a garbage sign is a disabled sign or otherwise.

If the apparatus(es) 102 can determine that a garbage sign is actually a disabled sign (i.e., the apparatus(es) 102 can recognize a disabled sign), the apparatus(es) 102 can, as an option, be further configured to recover a true sign from the disabled sign, as discussed earlier per the example implementation. As an option, when the apparatus(es) 102 determines that a garbage sign is actually a disabled sign, such information (e.g., the disabled sign) can, for example, be displayed (e.g., to a driver of the vehicle). As another option, it is contemplated that, in accordance with an embodiment of the disclosure, after a true sign is recovered, the traffic network can be updated for future reference (e.g., there can be a category of the true sign which is currently marked as a disabled sign). As mentioned earlier, an in-painting technique can be utilized for facilitate recovery of a true sign. For example, the aforementioned in-painting technique can include removal of one or more markers and filling that information with neighborhood segment information. It is contemplated that an objection of using in-painting technique can, for example, be to find exact information beneath the markers, classify it, and update an online traffic network database system. Moreover, as yet another option, it is contemplated that after in-painting, the apparatus(es) 102 can be configured to perform further classification (e.g., a second level classification). In regard to the second level classification, after in-painting, a true sign can be further classified. In one embodiment, the second classification can be performed by, for example, the second module 204 (e.g., by manner of classification-based processing). Further classification(s) in association with a true sign can, for example, include a first specific category and a second specific category. The first specific category can, for example, be associated with an optical character recognition (OCR) category (e.g., where the true sign is associable with only digits) and the second specific category can, for example, be associated with a picto category (e.g., where the true sign is associable with a pictogram representation). As yet a further option, in one embodiment, after a true sign is classified, the traffic control network database can be updated based on, for example, the aforementioned classification(s) in association with the true sign.

Alternatively, If the apparatus(es) 102 can determine that a garbage sign is not a disabled sign, the apparatus(es) 102 can be further configured to confirm/indicate that a garbage sign is an actual false positive sign (i.e., meaning such a sign is not a valid sign). The apparatus(es) 102 can, as an option, be configured to communicate information indicating/confirming that a garbage sign is an actual false positive sign for, for example, further processing (e.g., by the host device(s)), in accordance with an embodiment of the disclosure.

In view of the foregoing discussion, it is appreciable that, generally, the system 100 can be capable of recognizing one or more disabled signs, in accordance with an embodiment of the disclosure. Moreover, in one embodiment, the system 100 can be capable of facilitating the restoration of perception of the recognized disabled sign(s) (e.g., restoration/recovery of a true sign from a disabled sign).

As mentioned earlier, the present disclosure contemplates that it would be helpful to facilitate recognition of a disabled sign (e.g., a disabled traffic sign and/or a disabled road sign). In one embodiment, recognition of a disabled sign can, for example, be associated with restoring readability of information (i.e., which readability had been adversely affected) so that information intended to be conveyed can be properly perceived (e.g., by a driver and/or an autonomous vehicle).

Appreciably, by doing so, road safety (e.g., speed limits can be properly perceived by a driver) and/or operational reliability (of, for example, an autonomous vehicle) can possibly be improved. For example, a disabled speed limit sign could be erroneously perceived by a driver and/or an autonomous vehicle to be indicating a speed limit which is much lower/higher than the intended speed limit (e.g., an originally intended speed limit 80 could be erroneously perceived to be 90 if a portion of "8" is obscured; an originally intended speed limit of 120 could potentially lead to an erroneous perception that the speed limit is 10 if "2" is obscured). This could possibly lead to a vehicle being operated (by a driver and/or autonomously) at an unintended speed (e.g., at a higher speed than the legal speed limit/much lower than the legal speed) which could be undesirable (road safety and/or operational reliability concerns). By recognizing the disabled sign(s) and, optionally, restoring readability of information (i.e., which readability had been adversely affected) so that information intended to be conveyed can be properly perceived (e.g., by a driver and/or an autonomous vehicle), the possibility of unintended (e.g., unintended speed) operation of a vehicle can at least be reduced or, preferably, eliminated.

The present disclosure further contemplates that the above discussed classification model (e.g., in association with any one of the first classification level, the second classification level and the aforementioned further classification(s), or any combination thereof), processing/computational efficiency can possibly be facilitated.

For example, with classification of the sign(s) at multi-levels/layers and concatenation of such multi-levels/layers confidence can possibly be increased and this could facilitate less utilization of runtime and memory. Moreover, one or more new classifications (e.g., new category/categories) of sign(s) can be added, thereby increasing sign category coverage (i.e., by including one or more new categories existing known classifications) to support recognition capability/capabilities. Furthermore, this can possibly be useful for keeping Global Positioning System (GPS) data updated and valid for the end-users, thus potentially facilitating enhancement in regard to reliability and/or system robustness. Yet furthermore, the present disclosure contemplates that by recognition and/or classification as discussed above, confusion rate can possibly be reduced, leading potentially to an enhancement of performance and the driver (and/or autonomous vehicle) being alerted preemptively.

The aforementioned apparatus(es) 102 will be discussed in further detail with reference to Fig. 2 hereinafter.

Referring to Fig. 2, an apparatus 102 is shown in further detail in the context of an exemplary implementation 200, according to an embodiment of the disclosure.

In the exemplary implementation 200, the apparatus 102 can carry any one of a first 5 module 202, a second module 204, a third module 206, or any combination thereof In one embodiment, the apparatus 102 can carry a first module 202, a second module 204 and, optionally, a third module 206. In a specific example, the apparatus 102 can carry a first module 202, a second module 204 and a third module 206. In another specific example, the apparatus 102 can carry a first module 202 and a second module 204.

The first module 202 can be coupled to one or both of the second module 204 and the third module 206. The second module 204 can be coupled to one or both of the first module 202 and the third module 206. The third module 206 can be coupled to one or both of the first module 202 and the second module 204. Coupling between the first module 202, the second module 204 and/or the third module 206 can, for example, be by manner of one or both of wired coupling and wireless coupling. Each of the first module 202, the second module 204 and the third module 206 can correspond to one or both of a hardware-based module and a software-based module, according to an embodiment of the disclosure.

In one example, the first module 202 can correspond to a hardware-based receiver which can be configured to receive the input signal(s).

The second module 204 can, for example, correspond to a hardware-based processor which can be configured to perform one or more processing tasks based on the input signal(s) to produce one or more output signals.

The third module 206 can correspond to a hardware-based transmitter which can be configured to transmit the output signal(s).

The present disclosure contemplates the possibility that the first and third modules 202/206 can be an integrated software-based transceiver module (e.g., an electronic part which can carry a software program/algorithm in association with receiving and transmitting functions/an electronic module programmed to perform the functions of receiving and transmitting).

Earlier mentioned, the first module 202 can correspond to a hardware-based receiver which can be configured to receive the input signal(s). Additionally, the second module 204 can, for example, correspond to a hardware-based processor which can be configured to perform one or more one or more processing tasks on the received and/or generated input signal(s) to produce one or more output signals.

The input signal(s) can, for example, include can one or both of the data signal(s) and the reference signal(s) (i.e., the data signal(s) and/or the reference signal(s)), in accordance with an embodiment of the disclosure. The data signal(s) can, for example be communicated from the device(s) 104. The reference signal(s) can, for example, be communicated from the host device(s), in accordance with an embodiment of the disclosure.

The output signal(s) can, in one example, correspond to/include/be associated with one or more true signs (i.e., restored from corresponding one or more disabled signs), in accordance with an embodiment of the disclosure. The output signal(s) can, in another example, correspond to/include/be associated with an indication as to whether a received data signal can be associated with a disabled sign or not. In yet another example, the output signal(s) can correspond to/include/be associated with the true sign(s) and an indication as to whether a received data signal can be associated with a disabled sign or not.

The processing task(s) performed by the second module 204 can include any one of the aforementioned verification-based processing, classification-based processing, restoration-based processing and the second level classification, or any combination thereof.

In view of the foregoing, it is appreciable that the present disclosure generally contemplates an apparatus 102 which can, for example, be suitable for use for recognition of a disabled sign (e.g., a disabled traffic sign), in accordance with an embodiment of the disclosure. In one example, the apparatus 102 can be suitable for use with a vehicle.

The apparatus 102 can include a first module 202 and a second module 204 The first module 202 can be coupled to the second module 204.

The first module 202 can be configured to receive at least one input signal which can include at least one data signal and at least one reference signal.

The second module 204 can be configured to produce at least one output signal based on the data signal(s) and the reference signal(s). The data signal(s) can correspond to at least one read symbol which can be indicative of a spurious sign. The spurious sign can be associated with either a disabled sign or an actual false positive sign. The output signal(s) can, in one embodiment, be indicative of whether the spurious sign is a disabled sign or otherwise (ie, not a disabled sign such as an actual false positive sign).

In one embodiment, when the spurious sign is a disabled sign, the second module 204 can be configured to perform restoration-based processing such that a true sign can be recovered from a disabled sign. The restoration-based processing can, for example, be associated with at least one in-painting technique. In one example, the in-painting technique can facilitate information processing by manner of filling in missing information based on neighborhood segment information.

Moreover, in one embodiment, the second module 204 can be configured (e.g., by manner of classification-based processing) to classify the true sign. As mentioned earlier, the apparatus(es) 102 can be configured to perform, for example, a second level classification. In regard to the second level classification, after in-painting, a true sign can be further classified. Further classification(s) in association with a true sign can, for example, include a first specific category and a second specific category. The first specific category can, for example, be associated with an optical character recognition (OCR) category (e.g., where the true sign is associable with only digits) and the second specific category can, for example, be associated with a picto category (e.g., where the true sign is associable with a pictogram representation).

The above-described advantageous aspect(s) of the apparatus 102 of the present disclosure can also apply analogously (all) the aspect(s) of a below described processing method 300 of the present disclosure. Likewise, all below described advantageous aspect(s) of the processing method 300 of the disclosure can also apply analogously (all) the aspect(s) of above described apparatus 102 of the disclosure. It is to be appreciated that these remarks apply analogously to the earlier

discussed system 100 of the present disclosure

Referring to Fig. 3, a processing method 300 in association with the system 100 is shown, according to an embodiment of the disclosure.

The processing method 300 can be associated with the recognition of one or more disabled signs, in accordance with an embodiment of the disclosure. The processing method 300 can, as an option, be further associated with facilitating the restoration of perception of the recognized disabled sign(s) (e.g., restoration/recovery of a true sign from a disabled sign), in accordance with an embodiment of the disclosure.

The processing method 300 can include any one of a receiving step 302, a processing step 304 and an output generating step 306, or any combination thereof, in accordance with an embodiment of the disclosure.

In one embodiment, the processing method can include a receiving step 302, a 15 processing step 304 and an output step 306. In another embodiment, the processing method can include a receiving step 302 and a processing step 304.

With regard to the receiving step 302, the input signal(s) can be received by the apparatus(es) 102.

With regard to the processing step 304, the input signal(s) can be processed by the apparatus(es) 102 in a manner so as to generate the output signal(s).

With regard to the output step 306, the output signal(s) can be communicated from the apparatus(es) 102.

In this regard, the present disclosure generally contemplates, in one embodiment, a processing method 300 which can be usable for recognizing a disabled sign and/or restoration of a disabled sign.

The processing method can include a receiving step 302 and a processing step 304.

The receiving step 302 can include receiving (e.g., by the first module 202 of the aforementioned apparatus 102) at least one input signal which can include at least one data signal and at least one reference signal.

The processing step 304 can include processing (e.g., by the second module 204 of the aforementioned apparatus 102) the received data signal(s) and the reference signal(s) to generate at least one output signal.

In one embodiment, the processing step 304 can further include a restoration step (not shown). In regard to the restoration step, when the spurious sign is a disabled sign, restoration-based processing can be performed (e.g., by the second module of the aforementioned apparatus) to recover a true sign from the disabled sign.

Restoration-based processing can, for example, be associated with at least one in-painting technique. It is contemplated that the in-painting technique can be capable of facilitating information processing by manner of, for example, filling in missing information based on neighborhood segment information.

In one embodiment, the processing step 304 can further include a classification step (not shown). In regard to the classification step, classification-based processing can be performed to classify the true sign. As mentioned earlier, the apparatus(es) 102 can be configured to perform, for example, a second level classification. In regard to the second level classification, after in-painting, a true sign can be further classified.

Further classification(s) in association with a true sign can, for example, include a first specific category and a second specific category. The first specific category can, for example, be associated with an optical character recognition (OCR) category (e.g., where the true sign is associable with only digits) and the second specific category can, for example, be associated with a picto category (e.g., where the true sign is associable with a pictogram representation).

The present disclosure further contemplates a computer program (not shown) which can include instructions which, when the program is executed by a computer (not shown), cause the computer to carry out any one of, or any combination of, the receiving step 302, the processing step 304 and the output generating step 306, as discussed with reference to the processing method 300.

The present disclosure yet further contemplates a computer readable storage medium (not shown) having data stored therein representing software executable by a computer (not shown), the software including instructions, when executed by the computer, to carry out any one of, or any combination of, the receiving step 302, the processing step 304 and the output generating step 306, as discussed with reference to the processing method 300.

It should be appreciated that the embodiments described above can be combined in any manner as appropriate (e.g., one or more embodiments as discussed in the "Detailed Description" section can be combined with one or more embodiments as described in the "Summary of the Invention" section).

It should be further appreciated by the person skilled in the art that variations and combinations of embodiments described above, not being alternatives or substitutes, may be combined to form yet further embodiments.

In one example, the communication network 106 can be omitted, in accordance with an embodiment of the disclosure. Communication 0.e., between the apparatus(es) 102, the device(s) 104 and the host device(s), or any combination thereof) can be by manner of direct coupling. Such direct coupling can be by manner of one or both of wired coupling and wireless coupling.

In another example, the apparatus(es) 102 and the host device(s) can be considered to be a single device, in accordance with an embodiment of the disclosure. For example, the apparatus(es) 102 and the host device(s) can be integrated, in accordance with an embodiment of the disclosure.

In yet another example, the apparatus(es) 102 and one or more parts of the device 104 and/or the host device(s) can be considered to be a single device, in accordance with an embodiment of the disclosure. For example, the apparatus(es) 102 and one or more parts of the device(s) 104 and/or the host device(s) can be integrated, in

accordance with an embodiment of the disclosure.

In the foregoing manner, various embodiments of the disclosure are described for addressing at least one of the foregoing disadvantages. Such embodiments are intended to be encompassed by the following claims, and are not to be limited to specific forms or arrangements of parts so described and it will be apparent to one skilled in the art in view of this disclosure that numerous changes and/or modification can be made, which are also intended to be encompassed by the following claims.

Claims

Claim(s) 1. An apparatus (102) suitable for use for recognition of a disabled sign, the apparatus (102) comprising: a first module (202) configurable to: receive at least one input signal, the at least one input signal comprising: at least one data signal; and at least one reference signal, a second module (204) coupled to the first module (202), the second module (204) configurable to produce at least one output signal based on the at least one data signal and the at least one reference signal, wherein the at least one data signal corresponds to at least one read symbol being indicative of a spurious sign, the spurious sign being associable with one of a disabled sign and an actual false positive sign, and wherein the at least one output signal is indicative of whether the spurious sign is a disabled sign or an actual false positive sign.
2. The apparatus (102) according to claim 1, wherein when the spurious sign is a disabled sign, the second module (204) is configurable to perform restoration-based processing such that a true sign is recoverable from a disabled sign.
3. The apparatus (102) according to any of the preceding claims, wherein the restoration-based processing is associated with at least one in-painting technique.
4. The apparatus (102) according to any of the preceding claims, wherein the in-painting technique facilitates information processing by manner of filling in missing information based on neighborhood segment information.
5. The apparatus (102) according to any of the preceding claims, wherein the second module (204) is configurable to classify the true sign.
6. The apparatus (102) according to any of the preceding claims, wherein the disabled sign corresponds to a disabled traffic sign.
7. A processing method (300) usable for at least one of recognizing a disabled sign and restoration of a disabled sign, the processing method (300) comprising: a receiving step (302) comprising receiving, by a first module (202) of an apparatus (102) of any of the preceding claims, at least one input signal comprising: at least one data signal, and at least one reference signal; and a processing step (304) comprising processing, by a second module (204) of an apparatus (102) of any of the preceding claims, the received at least one data signal and at least one reference signal to generate at least one output signal, wherein the at least one data signal corresponds to at least one read symbol being indicative of a spurious sign, the spurious sign being associable with one of a disabled sign and an actual false positive sign, and wherein the at least one output signal is indicative of whether the spurious sign is a disabled sign or an actual false positive sign.
8. The processing method (300) as in claim 7, the processing step (304) further 20 comprising: a restoration step, wherein, when the spurious sign is a disabled sign, restoration-based processing is performed to recover a true sign from the disabled sign.
9. The processing method (300) as in claim 7 or claim 8, wherein the restoration-based processing is associated with at least one in-painting technique, and wherein the in-painting technique facilitates information processing by manner of filling in missing information based on neighborhood segment information
10. The apparatus (102) according to any of claims 7 to 9, the processing step (304) further comprising: a classification step wherein classification-based processing is performed to classify the true sign.
11. A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the receiving step (302) and the processing step (304) according to the processing method (300) of any of claims 7 to 10.
12. A computer readable storage medium having data stored therein representing software executable by a computer, the software including instructions, when executed by the computer, to carry out the receiving step (302) and the processing step (304) according to the processing method (300) of any of claims 7 to 10.