Object detection system, object detection method, and recording medium

Abstract

Provided are an object detection system, an object detection method, and a recording medium that can contribute to improving the accuracy of detection of an object by a plurality of sensors.　The object detection system comprises: a selection means that selects, on the basis of environment information indicating the external environment of a moving body, a combination of sensors having overlapping detection areas from among a plurality of sensors; and an integration means that integrates the outputs of the plurality of sensors by determining the identity of an object detected by the selected sensors.

Description

Object detection system, object detection method, and recording medium

[0001] The present invention relates to an object detection system, an object detection method, and a recording medium.

[0002] Patent Document 1 discloses a vehicle control system capable of executing appropriate driving support control based on a plurality of pieces of sensor information. The vehicle control system described in the document selects at least one piece of sensor information from among a plurality of pieces of sensor information indicating detection results of the same target object obtained by a plurality of sensors, based on the priority of sensor information that can be dynamically changed according to a predetermined criterion. Then, the vehicle control system selects at least one function from among a plurality of functions for safe driving support based on the selected at least one piece of sensor information. Then, the vehicle control system notifies the target vehicle of the selected at least one function.

[0003] Japanese Unexamined Patent Publication No. 2019-79454

[0004] Efforts have been made to utilize information obtained by object recognition using cameras and sensors for safe driving support and the like, but further improvement in accuracy is required. In this regard, the vehicle control system of Patent Document 1 only selects sensor information with higher accuracy from among a plurality of pieces of sensor information, and has a problem that object detection accuracy depends on the performance of the selected sensor.

[0005] The present disclosure aims to provide an object detection system, an object detection method, and a recording medium that can contribute to improving the accuracy of object detection by a plurality of sensors.

[0006] According to a first aspect, there is provided an object detection system comprising: selection means for selecting a combination of sensors having overlapping detection areas from among a plurality of sensors based on environmental information indicating an external environment of a mobile object; and integration means for integrating outputs of the plurality of sensors by determining the identity of an object detected by the selected sensors.

[0007] From a second perspective, an object detection method is provided that integrates the outputs of multiple sensors by selecting a combination of sensors with overlapping detection areas from among multiple sensors based on environmental information indicating the external environment of a moving object, and determining the identity of the object detected by the selected sensors.

[0008] From a third perspective, a recording medium is provided that contains a program that causes a computer to perform the following steps: selecting a combination of sensors with overlapping detection areas from among multiple sensors based on environmental information indicating the external environment of a moving object; and integrating the outputs of the multiple sensors by determining the identity of the object detected by the selected sensors.

[0009] This disclosure makes it possible to provide an object detection system, an object detection method, and a recording medium that can contribute to improving the accuracy of object detection using multiple sensors.

[0010] This is a diagram showing one configuration of this disclosure. This is a flowchart illustrating the operation of this disclosure. This is a diagram for explaining the operation of this disclosure. This is a diagram showing another configuration of this disclosure. This is a diagram showing one configuration of this disclosure. This is a flowchart illustrating another operation of this disclosure. This is a diagram for explaining the operation of this disclosure. This is a diagram showing the configuration of the computers that constitute the driver assistance system of this disclosure.

[0011] First, an overview of one embodiment of this disclosure will be described with reference to the drawings. In this disclosure, the drawings are associated with one or more embodiments. The reference numerals in the drawings appended to this overview are provided for convenience as examples to aid understanding and are not intended to limit this disclosure to the illustrated embodiments. In addition, the connecting lines between blocks in the drawings and other references referred to in the following description include both bidirectional and unidirectional lines. Unidirectional arrows schematically indicate the flow of the main signal (data) and do not exclude bidirectionality. The program is executed via a computer device, which includes, for example, a processor, a storage device, an input device, a communication interface, and a display device as needed. This computer device is also configured to communicate with devices (including computers) inside or outside the device via the communication interface, whether wired or wireless. In addition, there are ports or interfaces at the input / output connection points of each block in the figures, but these are omitted from the illustration.

[0012] In one embodiment, this disclosure can be realized by an object detection system 10 that is connected to a plurality of sensors S1 to S3 arranged in a predetermined detection area and comprises a selection means 11 and an integration means 12. More specifically, the selection means 11 selects a combination of sensors from the sensors S1 to S3 whose detection areas overlap, based on environmental information indicating the external environment of a moving object. More preferably, the selection means 11 selects a combination of sensors that achieves detection performance exceeding the detection performance of a single sensor from the plurality of sensors S1 to S3. This external environment includes time of day, brightness, weather, and the size of the detection area, which affect the accuracy of the sensors. Depending on the environmental information, the selection means 11 may select multiple sensors of the same type. Also, depending on the environmental information, the selection means 11 may select a single sensor instead of multiple sensors. In this case, the processing by the integration means 12 described later is omitted.

[0013] The integration means 12 integrates the outputs of the multiple sensors by determining the identity of the objects detected by the selected sensors. As described above, the multiple sensors selected by the selection means 11 detect more objects than would be detected by a single sensor. The integration means 12 confirms the consistency of these detected objects and integrates them.

[0014] The object detection system 10 configured as described above operates as follows. First, the object detection system 10 selects a combination of sensors from the plurality of sensors S1 to S3 whose detection areas overlap, based on environmental information (step S01 in Figure 2).

[0015] Next, the object detection system 10 integrates the outputs of the multiple sensors by determining the identity of the object detected by the selected sensor (step S02 in Figure 2).

[0016] Figure 3 is a diagram illustrating the operation of the present disclosure. In the example in Figure 3, the selection means 11 selects sensors S1 and S2 from among sensors S1 to S3. In this case, sensors S1 and S2 each detect a pedestrian P. The integration means 12 integrates the outputs of the multiple sensors by determining the identity of the objects captured by sensors S1 and S2. In the example in Figure 3, both sensors S1 and S2 are able to capture the pedestrian P, but with respect to the vehicle V, sensor S1 cannot capture the entire vehicle V due to the relative position of sensor S1 and the vehicle. In this case, sensor S1 alone may fail to detect the vehicle V. Also, in sensor S2, part of the vehicle V is hidden by the pedestrian P. In this case as well, sensor S2 alone may misdetect the vehicle V as another object. According to the configuration of the present disclosure, by determining the identity of the vehicle V captured by sensors S1 and S2, the vehicle V can be reliably captured. Factors that may affect the sensor output include, in addition to the occlusion mentioned above, ambient brightness, weather, and reflections of obstacles. According to the configuration of this disclosure, even if the selected sensor is affected by these factors, if the object can be captured by the entire group of sensors, the likelihood of correctly detecting the object can be increased. In the example in Figure 3, two sensors S1 and S2 are selected, but the detection performance can be improved by selecting three or more sensors whose sensing ranges overlap.

[0017] As described above, according to this embodiment, the object detection capability can be enhanced by comprehensively using sensors S1 to S3. This is because the selection of sensors by the selection means 11 enhances the detection performance of objects present in the detection area, and because the sensor outputs are integrated, detection omissions and false detections can be reduced.

[0018] Furthermore, as shown in Figure 4, the object detection system of this disclosure can also be mounted on a moving object such as a vehicle. In this case as well, the object detection system 10a uses the selection means 11 to select multiple sensors mounted on the moving object whose detection areas overlap, and integrates their outputs to detect objects around the moving object.

[0019] The objects that the object detection system of this disclosure can detect are not particularly limited, but may include the person being authenticated or parts of the human body. By using the mechanism of this disclosure, it is possible to prevent misidentification and detection errors and improve the recognition accuracy of the entire authentication system.

[0020] [First Embodiment] Next, a first embodiment in which the present disclosure is applied to a driver assistance system that provides driving assistance to vehicles traveling on roads will be described. Figure 5 is a diagram showing one configuration of the present disclosure. Referring to Figure 5, a driver assistance system 100 connected to cameras C1 and C2, LiDAR (Light Detection And Ranging) L1, radar R1, and illuminance sensor S is shown. As will be described later, this driver assistance system 100 is equipped with an object detection function and corresponds to the object detection system 10 described above.

[0021] Cameras C1 and C2 are, for example, cameras installed on the road to be monitored, with overlapping shooting ranges. Alternatively, cameras C1 and C2 may be a combination of a camera capable of capturing visible light images and a camera capable of capturing infrared images. Hereafter, cameras C1, C2, LiDAR L1, and radar R1 will be collectively referred to as "sensors." Also, in the example in Figure 5, there are two cameras, one LiDAR L1, and one radar R1, but there are no restrictions on the number of these.

[0022] The driver assistance system 100 includes a selection unit 101, an integration unit 102, a correction unit 103, a domain information storage unit 104, a distribution unit 105, and an external information acquisition unit 106.

[0023] The external information acquisition unit 106 acquires weather information, time, etc., for the vicinity of the road being monitored from a server 200 located on the internet or elsewhere.

[0024] The selection unit 101 selects sensors for detecting vehicles and pedestrians within the detection area set on the road, based on the information provided by the external information acquisition unit 106 and the illuminance information output from the illuminance sensor S, and sends the selected sensors to the integration unit 102. For example, if the detection area is sunny and the time is daytime, the selection unit 101 selects cameras C1 and C2. Also, for example, if the detection area is foggy, the selection unit 101 selects LiDAR L1 and radar R1 in addition to cameras C1 and C2. The selection unit 101 corresponds to the selection means 11 described above. Furthermore, the information provided by the external information acquisition unit 106 and the illuminance information correspond to environmental information indicating the external environment.

[0025] The integration unit 102 includes a reliability information assignment unit (assignment means) 1021. The reliability information assignment unit 1021 assigns reliability information to the results output by each sensor, taking into account the unique characteristics of each sensor.

[0026] This reliability information can take into account not only the accuracy of the sensor output but also its freshness. Because each sensor has a different sensing principle and mechanism, the output data also has a different temporal expiration date. For example, images captured by cameras C1 and C2 are cropped images of a predetermined detection area, and the objects captured in each image exist at the time the image was taken, but they may not still exist after a certain period of time. Similarly, the reliability of data obtained from LiDAR L1 and radar R1 also decreases over time.

[0027] The integration unit 102 integrates the outputs of the selected sensors by determining the identity of the objects detected by each sensor using the reliability information as described above. More specifically, the integration unit 102 also uses the reliability information to retain objects that are detected by multiple sensors and are consistent, as well as data obtained from sensors with relatively high accuracy. Furthermore, the integration unit 102 also uses the reliability information to delete objects that are inconsistent between sensors or objects detected by sensors with relatively low accuracy. Finally, the integration unit 102 sends the integrated sensor outputs to the correction unit 103.

[0028] The domain information storage unit 104 stores background information such as information on backlit time periods for each sensor in the detection target area (position of light source), traffic volume, topography, and the presence or absence of obstacles such as plants and signs.

[0029] The correction unit (correction means) 103 retrieves domain information for the corresponding detection area from the domain information storage unit 104 and corrects the integrated sensor output as necessary. For example, if the images from cameras C1 and C2 are affected by backlighting, the correction unit 103 performs a correction to remove the backlighting effect. Also, for example, if the sensor output is affected by an obstacle in the detection area, the correction unit 103 performs a correction to remove the effect of the obstacle. Possible correction methods in this case include comparing the output with pre-prepared background information and removing the affected portion.

[0030] For example, if domain information provides information about traffic volume in the detection area, the correction unit 103 corrects the detection results of each sensor, taking traffic volume into consideration. Specifically, if the domain information indicates that traffic volume is low during the relevant time period, the correction unit 103 strictly determines whether the object detected by the sensor is a vehicle or not. Conversely, if the domain information indicates that traffic volume is high during the relevant time period, the correction unit 103 loosely determines whether the object detected by the sensor is a vehicle or not. Finally, the correction unit 103 sends the corrected sensor output to the distribution unit 105.

[0031] The distribution unit (distribution means) 105 uses the corrected sensor output to create safety information or driving support information, including information about objects present in the detection area, and distributes it to the vehicle V. This vehicle V may include, for example, an autonomous vehicle. This information may be transmitted directly from the distribution unit 105 to the vehicle V, or it may be transmitted via a roadside unit or a MEC (Multi-access Edge Computing) node. In addition, the distribution unit 105 may also transmit safety information and driving support information to a control center or the like that manages the operation of the vehicle V.

[0032] Next, the operation of this embodiment will be described in detail with reference to the drawings. Figure 6 is a flowchart showing the operation of the driver assistance system 100 of this embodiment. First, the driver assistance system 100 selects a combination of sensors based on the information provided by the external information acquisition unit 106 and the illuminance information output from the illuminance sensor S (step S001).

[0033] Next, the driver assistance system 100 adds reliability information to the output obtained from the selected sensor (step S002). Furthermore, the driver assistance system 100 uses the reliability information to integrate the outputs of the selected sensor (step S003).

[0034] Next, the driver assistance system 100 corrects the integrated sensor output using domain information (step S004).

[0035] Finally, the driver assistance system 100 delivers driver assistance information to the vehicle V, including information about objects present in the detection area (step S005).

[0036] Figure 7 is a diagram illustrating the operation of the present disclosure. The solid triangles in Figure 7 conceptually represent the sensing ranges of cameras C1 and C2. The dashed triangle in Figure 7 conceptually represents the sensing range of LiDAR L1. It should be noted that the sensing ranges in Figure 7 are purely conceptual and may differ from the actual sensing ranges of cameras and LiDARs.

[0037] The driver assistance system 100 selects a combination of sensors from cameras C1, C2, LiDAR L1, and radar R1 to sense the detection area based on information provided by the external information acquisition unit 106, illuminance information, etc. For example, the driver assistance system 100 selects cameras C1, C2, and radar R1. The driver assistance system 100 then integrates the outputs of these sensors by retaining highly reliable objects detected by cameras C1, C2, and radar R1 and removing less reliable ones. For example, if an object detected by camera C1 is also detected by radar R1, the driver assistance system 100 treats the object as existing. On the other hand, if an object detected by camera C1 is not detected by radar R1, the driver assistance system 100 can also treat the object as not existing. Furthermore, when integrating the outputs of the sensors, the driver assistance system 100 may refer to domain information.

[0038] The sensor selection illustrated in Figure 7 is an over-selection from the perspective of capturing the vehicle V1. However, in this disclosure, after deliberately making an over-selection, integration processing (cleansing) is performed in the integration unit 102. By doing so, it is possible to reduce the chances of missing or falsely detecting the vehicle V1 shown in Figure 7.

[0039] Furthermore, in Figure 7, if the light source is on the left side, cameras C1 and C2 will capture the vehicle V1 in a backlit state. However, in this embodiment, correction is performed using domain information, which makes it possible to suppress a decrease in the output quality of the sensors.

[0040] While the embodiments of this disclosure have been described above, this disclosure is not limited to the embodiments described above, and further modifications, substitutions, and adjustments can be made without departing from the basic technical concept of this disclosure. For example, the network configurations, element configurations, and data representations shown in the drawings are examples to aid in understanding this disclosure and are not limited to the configurations shown in these drawings.

[0041] For example, in the above-described embodiment, the description has been given on the assumption that correction is performed by the correction unit 103 after integration of sensor outputs. However, correction based on domain information may be performed before or after addition of reliability information. In this case, addition of reliability information and integration of outputs will be performed after correction based on domain information.

[0042] Furthermore, in the above-described embodiment, the description has been given on the assumption that the driving support system 100 receives data from the illuminance sensor S. However, instead of using the illuminance sensor S, the brightness of the detection area may be estimated from images captured by cameras C1 and C2. In this case, the driving support system 100 can adopt a configuration in which it receives real-time images from the cameras C1 and C2, and estimates the illuminance based on the luminance of the images and scene analysis.

[0043] Furthermore, in the above-described embodiment, the description has been given on the assumption that the driving support system 100 acquires weather information, time and the like near the monitored road from the external server 200. However, the server 200 may also receive more specific sensor selection instructions. In this case, the driving support system 100 transmits information of the detection area and the like to the server 200 that has a function equivalent to the selection unit 101 described above, and receives the sensor selection instruction.

[0044] Furthermore, in the example of FIG. 7, the camera C1, the camera C2, and the LiDAR L1 oriented in the same direction are selected. However, the driving support system 100 may select sensors and cameras oriented in different directions. In this case, similarly, the driving support system 100 integrates the outputs of the selected sensors by determining the identity of objects detected by each sensor.

[0045] (Regarding Hardware Configuration) In each embodiment of this disclosure, each component of each device represents a functional unit block. Some or all of each component of each device is realized by any combination of an information processing device 900 and a program, for example, as shown in Figure 8. Figure 8 is a block diagram showing an example of the hardware configuration of the information processing device 900 that realizes each component of each device. The information processing device 900 includes, as an example, the following configuration: ・CPU (Central Processing Unit) 901 ・ROM (Read Only Memory) 902 ・RAM (Random Access Memory) 903 ・Program 904 loaded into RAM 903 ・Storage device 905 that stores the program 904 ・Drive device 907 that reads and writes to the recording medium 906 ・Communication interface 908 that connects to a communication network 909 ・Input / output interface 910 that performs data input and output ・Bus 911 that connects each component

[0046] Each component of each device in each embodiment is realized by the CPU 901 acquiring and executing a program 904 that realizes these functions. That is, the CPU 901 in Figure 8 executes a sensor selection program and a data integration program, and performs update processing of each calculation parameter held in the RAM 903, storage device 905, etc. The program 904 that realizes the functions of each component of each device is, for example, stored in advance in the storage device 905 or ROM 902, and read by the CPU 901 as needed. The program 904 may be supplied to the CPU 901 via a communication network 909, or it may be stored in advance in a recording medium 906, and the drive device 907 may read the program and supply it to the CPU 901.

[0047] There are various modified examples of implementation methods for each device. For example, each device may be implemented by any combination of a separate information processing apparatus 900 and a program for each individual component. Further, a plurality of components included in each device may be implemented by any combination of one information processing apparatus 900 and a program. That is, each unit (processing means, function) of the object detection system described above can be implemented by a computer program that causes a processor mounted in the apparatus to execute each process described above using the hardware of the processor.

[0048] Further, part or all of each component of each device is implemented by other general-purpose or special-purpose circuits, processors, or a combination thereof. These may be configured by a single chip, or may be configured by a plurality of chips connected via a bus.

[0049] Part or all of each component of each device may be implemented by a combination of the above-described circuits or the like and a program.

[0050] When part or all of each component of each device is implemented by a plurality of information processing apparatuses, circuits, or the like, the plurality of information processing apparatuses, circuits, or the like may be arranged centrally or distributedly. For example, the information processing apparatuses, circuits, or the like may be implemented as a form in which each is connected via a communication network, such as a client-server system or a cloud computing system.

[0051] It should be noted that each of the above-described embodiments is a preferred embodiment of the present disclosure, and the scope of the present disclosure is not limited only to the above embodiments. That is, those skilled in the art can make modifications and substitutions to the above embodiments and construct various modified forms without departing from the gist of the present disclosure.

[0052] Part or all of the above-described embodiments can also be described as in the following supplementary notes, but are not limited thereto.

[0053] [Note 1] An object detection system comprising: a selection means for selecting a combination of sensors from a plurality of sensors whose detection areas overlap, based on environmental information indicating the external environment of a moving object; and an integration means for integrating the outputs of the plurality of sensors by determining the identity of the object detected by the selected sensors. [Note 2] The selection means of the object detection system described above can be configured to select a combination of sensors that achieves detection performance exceeding the detection performance of a single sensor among the plurality of sensors. [Note 3] The object detection system described above can further be configured to include a provisioning means for providing reliability information to the output of the sensors, and the integration means can be configured to integrate the outputs of the selected sensors using the reliability information. [Note 4] The object detection system described above can further be configured to include a correction means for correcting the detection result using domain knowledge describing environmental factors. [Note 5] The domain knowledge of the object detection system described above is the position of a light source in each time period, and the correction means can be configured to correct the detection result considering the position of the light source. [Note 6] The domain knowledge of the object detection system described above is the traffic volume in each time period, and the correction means can be configured to correct the detection result taking the traffic volume into consideration. [Note 7] The domain knowledge of the object detection system described above is information about obstacles that affect the output of the sensors at the location where each sensor is installed, and the correction means can be configured to correct the detection result taking the obstacles into consideration. [Note 8] The integration means of the object detection system described above can be configured to integrate the outputs of the selected sensors by comparing the outputs of the selected sensors and selecting the outputs that are consistent. [Note 9] The object detection system described above can further be configured to include a distribution means that generates safety information indicating the presence of the detected object based on the correction result and transmits it to a predetermined device.[Appendix 10] An object detection method that, based on environmental information indicating the external environment of a moving object, selects a combination of sensors from a plurality of sensors whose detection areas overlap, and integrates the outputs of the plurality of sensors by determining the identity of the object detected by the selected sensors. [Appendix 11] A recording medium that stores a program that causes a computer to execute the following: a process of selecting a combination of sensors from a plurality of sensors whose detection areas overlap based on environmental information indicating the external environment of a moving object, and a process of integrating the outputs of the plurality of sensors by determining the identity of the object detected by the selected sensors. The forms described in each of the above appendices can be combined with each other after making the necessary modifications. For example, a configuration that combines the contents of appendix 2 and appendix 3 is also included in the scope of disclosure of this specification. In this case, the object detection system will have a function to add reliability information to the sensor output and a function to correct the detection result using domain knowledge. The forms described in appendix 10 and appendix 11 can be expanded into the forms of appendix 2 to 9, similar to appendix 1.

[0054] Furthermore, each disclosure in the above-mentioned patent documents is incorporated into this document by reference and may be used as the basis or part of this disclosure as necessary. Within the framework of this disclosure (including the claims), further modifications and adjustments to the embodiments or examples are possible based on their fundamental technical concept. Also, within the framework of this disclosure, various combinations or selections (including partial deletions) of various disclosure elements (including each element of each claim, each element of each embodiment or example, each element of each drawing, etc.) are possible. In other words, this disclosure naturally includes the entire disclosure, including the claims, and various modifications and alterations that a person skilled in the art could make in accordance with the technical concept. In particular, with respect to the numerical ranges described in this document, any numerical value or sub-range included within that range should be interpreted as being specifically described, even if not otherwise stated. Furthermore, each disclosure item of the above-mentioned cited documents may, as necessary, be used in part or in whole as part of this disclosure, in accordance with the spirit of this disclosure, and this is also considered to be included in the disclosure items of this application.

[0055] 10, 10a Object detection system 11 Selection means 12 Integration means 100 Driving support system 101 Selection unit 102 Integration unit 103 Correction unit 104 Domain information storage unit 105 Distribution unit 106 External information acquisition unit 900 Information processing device 901 CPU (Central Processing Unit) 902 ROM (Read Only Memory) 903 RAM (Random Access Memory) 904 Program 905 Storage device 906 Recording medium 907 Drive device 908 Communication interface 909 Communication network 910 Input / output interface 911 Bus C1, C2 Camera L1 LiDAR R1 Radar S Illuminance sensor S1-S3 Sensor V, V1 Vehicle

Claims

1. An object detection system comprising: a selection means for selecting a combination of sensors with overlapping detection areas from among multiple sensors based on environmental information indicating the external environment of a moving object; and an integration means for integrating the outputs of the multiple sensors by determining the identity of the object detected by the selected sensors.

2. The object detection system according to claim 1, wherein the selection means selects a combination of sensors to achieve detection performance that exceeds the detection performance of one of the plurality of sensors individually.

3. The object detection system according to claim 1 or 2, further comprising a means for assigning reliability information to the output of the sensor, wherein the integration means integrates the output of the selected sensor using the reliability information.

4. An object detection system according to any one of claims 1 to 3, further comprising a correction means for correcting the detection result using domain knowledge describing environmental factors.

5. The object detection system according to claim 4, wherein the domain knowledge is the position of a light source in each time period, and the correction means corrects the detection result taking into account the position of the light source.

6. The object detection system according to claim 4, wherein the domain knowledge is the traffic volume in each time period, and the correction means corrects the detection result taking the traffic volume into consideration.

7. The object detection system according to claim 4, wherein the domain knowledge is information relating to obstacles that affect the output of the sensors at the locations where each sensor is installed, and the correction means corrects the detection result taking the obstacles into consideration.

8. The object detection system according to any one of claims 1 to 7, wherein the integrating means integrates the outputs of the selected sensors by comparing the outputs of the selected sensors and selecting the outputs that are consistent.

9. An object detection system according to any one of claims 1 to 8, further comprising distribution means for generating safety information indicating the presence of the detected object based on the correction result and transmitting it to a predetermined device.

10. An object detection method that integrates the outputs of multiple sensors by selecting a combination of sensors whose detection areas overlap from among multiple sensors based on environmental information indicating the external environment of a moving object, and determining the identity of the object detected by the selected sensors.

11. A recording medium that contains a program that causes a computer to perform the following steps: selecting a combination of sensors from among multiple sensors whose detection areas overlap based on environmental information indicating the external environment of a moving object; and integrating the outputs of the multiple sensors by determining the identity of the object detected by the selected sensors.

Images