A control system for use in a vehicle

Abstract

A system and method for controlling exterior lights 20 of a vehicle 10 to illuminate an under-illuminated area, for example so that driver assistance systems can be used in low-lighting conditions. Th

Description

TECHNICAL FIELD The present disclosure relates to a control system for use in a vehicle. Aspects of the invention relate to a vehicle, and a method for controlling a vehicle BACKGROUND Vehicles are often provided with a variety of driver assistance systems which aid or otherwise enhance the driving experience of the vehicle. These systems can include the provision of visualisation systems which provide the driver with additional views of the vehicle which they may not otherwise have convenient access to. The systems may also include autonomous drive systems (e.g. autonomous parking systems) which are able to manoeuvre the vehicle without input from the driver. Typically such systems require a threshold level of lighting in order to operate correctly. As a result, when the car is being operated in a poorly lit environment (e.g, in garages, when operating the vehicle at night) these systems may function incorrectly or may be unusable. Prior art systems will then typically simply prevent use of the driver assistance systems where the light level is below the threshold. It is an aim of the present invention to address one or more of the disadvantages associated with the prior art. SUMMARY OF THE INVENTION Aspects and embodiments of the invention provide a control system for use in a vehicle, a vehicle, and a method for controlling a vehicle, as claimed in the appended claims. According to an aspect of the present invention, there is provided a control system for use in a vehicle. The control system comprises one or more processors collectively configured to receive an indication that an image, captured by one or more cameras of the vehicle, of an area proximate to the vehicle is underilluminated. Upon receipt of the indication, the one or more processors are collectively configured to instruct an exterior lighting system of the vehicle to illuminate the area proximate to the vehicle. Subsequently, the one or more processors are collectively configured to receive, from the one or more cameras, a plurality of images of the illuminated area proximate to the vehicle, and generate, based on the plurality of images of the illuminated area, a volumetric reconstruction of the illuminated area proximate to the vehicle. The control system of the present aspect is advantageous as this enables the use of driver assistance systems of the vehicle in low lighting conditions. In particular, driver assistance systems (such as visualisation systems and autonomous driving systems) typically require a threshold level of illumination to function correctly, meaning that these systems become unusable in under illuminated areas (i.e. areas in which there is insufficient lighting to enable functionality of the driver assistance systems, such as underground garages). The present system mitigates against this by illuminating the poorly lit areas and generating a volumetric reconstruction which can subsequently be utilised by driver assistance systems. Optionally, the one or more processors may be collectively configured to, upon receipt of the indication, instruct a torque system of the vehicle to slow or stop the vehicle prior to instructing the exterior lighting system to illuminate the area proximate to the vehicle. This can advantageously increase the quality of the captured images by reducing motion blur in the images. The one or more processors may be collectively configured to receive positional data of the vehicle from a navigational system of the vehicle, and update, based on the received positional data, the volumetric reconstruction of the illuminated area proximate to the vehicle. This can advantageously enable the volumetric reconstruction to be accurate, even where the vehicle has moved. Further optionally the one or more processors may be collectively configured to render a view of the illuminated area based on the volumetric reconstruction of the illuminated area, receive positional data of the vehicle from a navigational system of the vehicle, and generate, based on the received positional data and the volumetric reconstruction of the illuminated area, a second view of the illuminated area proximate to the vehicle. This may advantageously enable use of driver assistance systems based on a single set of captured images. In some embodiments of this aspect, the one or more processors may be collectively configured to upon receipt of the indication, instruct an exterior lighting system of the vehicle to continuously illuminate the area proximate to the vehicle over a time period, receive, from the one or more cameras, a continuous stream of a plurality of images of the illuminated area proximate to the vehicle over the time period, and update, based on a plurality of images of the illuminated area received subsequent to the generation of the volumetric reconstruction of the illuminated area proximate to the vehicle, the generated volumetric reconstruction of the illuminated area proximate to the vehicle. Optionally, the one or more processors may be collectively configured to generate a single merged image of the illuminated area by merging the plurality of images. In such optional embodiments, the one or more processors may be configured to identify, from the plurality of images, two or more images each comprising respective image data representative of a common region of the illuminated area, select the respective image data having a highest illumination of the common region, and generate the single merged image using, for the common region, the respective image data having the highest illumination. Further optionally, the plurality of images may comprise one or more sets of multiple images, each set of multiple images being captured by a camera of the one or more cameras and the one or more processors may be collectively configured to generate a single merged image for each camera of the one or more cameras by merging the set of multiple images captured by the corresponding camera. In such optional embodiments, the one or more processors may be collectively configured to, for each set of images, identify, from the set of multiple images, two or more images each comprising respective image data representative of a common region of the illuminated area, select the respective image data having a highest illumination of the common region, and generate the single merged image using, for the common region, the respective image data having the highest illumination. In some embodiments, the exterior lighting system may comprise one or more adaptive headlights of the vehicle, and the one or more processors may be collectively configured to instruct the one or more adaptive headlights to illuminate the area proximate to the vehicle by instructing the adaptive headlights to perform a sweep of the area proximate to the vehicle. In such embodiments, the sweep of the adaptive headlights may sweep through a 180° arc. Optionally, the one or more processors may be collectively configured to provide the volumetric reconstruction to a display system of the vehicle for display to a vehicle occupant. Further optionally, the one or more processors may be collectively configured to provide the volumetric reconstruction as input data to an autonomous drive system of the vehicle. In such embodiments, the autonomous drive system may comprise an autonomous parking functionality, a steering assist functionality, an automatic braking functionality, or a combination thereof. In some embodiments, the one or more processors may be collectively configured to generate the volumetric reconstruction using a Neural Radiance Field, NeRF, algorithm. The NeRF algorithm may be conditioned based on the exposure of the plurality of images of the illuminated area proximate to the vehicle. According to a second aspect of the present invention, there comprises a vehicle. The vehicle comprises one or more cameras, an exterior lighting system, and the control system of any embodiments of the aspect of the invention described previously. In some embodiments of this aspect, the vehicle may further comprise an autonomous parking system, wherein the autonomous parking system is configured to control a position of the vehicle based on the volumetric reconstruction of the illuminated area proximate to the vehicle, and provide an indication of the position of the vehicle to the control system, wherein the control system is configured to update the volumetric reconstruction of the illuminated area proximate to the vehicle based on the indication of the position of the vehicle. According to a third aspect of the present invention, there comprises a method for controlling a vehicle. The method comprises firstly receiving, at a control system of the vehicle, an indication that an image, captured by one or more cameras of the vehicle, of an area proximate to the vehicle is under-illuminated. The method further comprises, upon receipt of the indication, instructing, by the control system, an exterior lighting system of the vehicle to illuminate the area proximate to the vehicle. The method further comprises receiving, at the control system from the one or more cameras, a plurality of images of the illuminated area proximate to the vehicle, and generating, based on the plurality of images of the illuminated area, a volumetric reconstruction of the illuminated area proximate to the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS One or more embodiments of the invention will now be described, by way of example only, with reference to the accompanying drawings, in which: Figure 1 shows a vehicle in accordance with an embodiment of the invention; Figure 2 shows a control system in accordance with an embodiment of the present invention for controlling a vehicle; Figure 3 shows a use scenario for the control system of Figure 2; Figure 4 shows a method of controlling the control system of Figure 2 in accordance with an embodiment of the present invention; and Figure 5 shows a further method of controlling the control system of Figure 2 in accordance with an embodiment of the present invention. DETAILED DESCRIPTION A vehicle 10 in accordance with an embodiment of the present invention is described herein with reference to the accompanying Figure 1. With reference to Figure 1, the vehicle 10 comprises a control system 100 (described in more detail with reference to Figure 2), an exterior lighting system 20, and one or more cameras 30. In Figure 1, the exterior lighting system 20 is shown as headlights of the vehicle 10, however it is to be appreciated that this is for illustrative purposes only, and that in the present invention, any exterior lighting system 20 suitably adapted to enable the functionality described herein may be used. Similarly, in Figure 1 only one camera 30 is shown, however it is to be appreciated that additional cameras 30 may also be provided to enable the functionalities described herein. The control system 100 is in communication with the exterior lighting system 20 and the one or more cameras 30. The one or more cameras 30 are configured to capture images of an area proximate to the vehicle 10. In some embodiments, the one or more cameras 30 may be configured to capture discrete single images. In other embodiments, the one or more cameras 30 are configured to capture video footage of the area proximate to the vehicle 10. In some embodiments, the area proximate to the vehicle 10 comprises an area within 5m of the exterior of the vehicle 10. The one or more cameras 30 may additionally be configured to determine the level of illumination in images captured by the one or more cameras 30. In particular, the one or more cameras 30 may be configured to determine whether one or more of the captured images is under-illuminated. This may comprise determining that the level of illumination in one or more of the captured images is below a particular threshold level required for the operation of one or more driver assistance systems 40 provided within the vehicle 10. The threshold level may be a single predetermined value for all of the one or more driver assistance systems 40. Alternatively, the threshold level may be set such that the value varies in dependence upon the requirements of each of the one or more driver assistance systems 40. Additionally or alternatively, the vehicle 10 may be provided with a separate vehicle processor 130 (or any other suitably configured vehicle system) which is configured to receive the images captured by the one or more cameras 30 and perform the determination of whether the level of illumination in the captured images is below a particular threshold level required for the operation of one or more driver assistance systems 40 of the vehicle 10, In some embodiments, the control system 100 may be configured to directly receive the images captured by the one or more cameras 30 and perform the determination of whether one or more of the captured images is under-illuminated. The driver assistance systems 40 may comprise one or more systems disposed within the vehicle 10 which may be in communication with the control system 100 which aid or otherwise enhance the driving experience of the vehicle 10 and which will typically require image data of an area proximate to the vehicle 10. Such systems may include visualisation systems which provide the driver with additional views of the vehicle 10 which they may not otherwise have convenient access to. The systems may also include autonomous drive systems (e.g. autonomous parking systems) which are able to manoeuvre the vehicle 10 without input from the driver, based on image data of the area proximate to the vehicle 10. In each case, without the provision of sufficient illumination within the image data, the driver assistance system 40 may not be able to function properly or at all. For example, in the case of a visualisation system, under-illuminated image data will result in the driver being provided with a dark images which are hard to interpret. In the case of autonomous drive systems, the system may be unable to manoeuvre in the area proximate to the vehicle 10 since it may not have sufficient data to ascertain the dimensions of the area or of any potential obstructions in the area. It is to be appreciated that each form of driver assistance system 40 may have different illumination requirements in order for the functionality of the system to be enabled (i.e., different thresholds) and that in present embodiments, the one or more cameras 30 and / or the vehicle processor 130 may be appropriately configured to determine whether the level of illumination meets each of the threshold requirements. In some embodiments of the present invention, the exterior lighting system 20 comprises one or more adaptive headlights. In such embodiments, the adaptive headlights may comprise one or more light sources which are configured to be able to rotate such that the light emitted from the one or more light sources is able to be rotated. In some instances within this embodiment, the degree of rotation of the one or more light sources of the adaptive headlights is such that an arc of light may be swept out by the adaptive headlights at an angle up to and including 180° in front of the adaptive headlights. With reference to Figure 2, there is illustrated a control system 100 for use in a vehicle 10 such as the one illustrated in Figure 1. The control system 100 comprises one or more controllers 110. The control system 100 is configured to receive an indication 135 from the one or more cameras 30, the vehicle processor 130 or any other suitably configured system of the vehicle 10 (in accordance with embodiments described above) that one or more images captured by the one or more cameras 30 of an area proximate to the vehicle 10 is under-illuminated. The control system 100 may then output a control signal 155 to control the exterior lighting system 20 of the vehicle 10. In particular, the control system 100 may be configured to output a control signal 155 which instructs the exterior lighting system 20 to illuminate the area proximate to the vehicle 10. The control system 100 is further configured to receive a plurality of captured images from the one or more cameras 30. In particular, the control system 100 is configured to receive these images subsequent to the control signal 155 being outputted. The captured images which are received are of the area proximate to the vehicle 10 which have been illuminated by the exterior lighting system 20 as a result of the outputted control signal 155. The control system 100 may then generate, on the basis of the received plurality of images of the illuminated area, a volumetric reconstruction of the illuminated area proximate to the vehicle 10. The volumetric reconstruction may comprise a three dimensional model of the illuminated area proximate to the vehicle 10 which enables the generation of views from a plurality of positions from within the three dimensional model Additional detail regarding the volumetric reconstruction and its generation is provided below. The control system 100 as illustrated in Figure 1 comprises one controller 110, although it will be appreciated that this is merely illustrative. The controller 110 comprises processing means 120 and memory means 125. The processing means 120 may be one or more electronic processing device 120 which operably executes computer-readable instructions. The memory means 125 may be one or more memory devices. The memory means 125 is electrically coupled to the processing means 120. The memory means 125 is configured to store instructions, and the processing means 120 is configured to access the memory means 125 and execute the instructions stored thereon. The processing means 120 may be configured to execute the instruction to generate the control signal 155 to be outputted, and to generate the volumetric reconstruction of the illuminated area proximate to the vehicle 10 in accordance with embodiments described above. The controller 110 comprises an input means 140 and an output means 150. The input means 140 may comprise an electrical input of the controller 110. The output means 150 may comprise an electrical output of the controller 110. The input 140 is arranged to receive an under-illumination signal 165 from the one or more cameras 30, the vehicle processor 130 or any other suitably configured system of the vehicle 10 (in accordance with embodiments described above). The under-illumination signal 165 is an electrical signal which is indicative of one or more images captured by the one or more cameras 30 of an area proximate to the vehicle 10 being under-illuminated. The output 150 is arranged to output a lighting control signal 155 for controlling the exterior lighting system 20 to illuminate the area proximate to the vehicle 10. The input means 140 is further arranged to receive a plurality of captured images 170 from the one or more cameras 30 subsequent to the control signal 155 being outputted to the exterior lighting system 20. The captured images which are received are of the area proximate to the vehicle 10 which have been illuminated by the exterior lighting system 20 as a result of the outputted control signal 155. The processing means 120 is further configured to use the received images of the illuminated area proximate to the vehicle 10 in order to generate a volumetric reconstruction of the illuminated area proximate to the vehicle 10. This may be achieved by execution of a volumetric reconstruction algorithm which may be stored within the memory means 125 in the form of instructions to be executed. In optional embodiments, the controller 110 may be configured to provide, via the output means 150 the volumetric reconstruction via a data signal 160 to a driver assistance system 40 of the vehicle 10. In some embodiments, the processing means 120 may be configured to generate simulated views based upon the volumetric reconstruction and these may be configured to be provided, via the output means 150, to a driver assistance system 40 of the vehicle 10. Referring to Figure 3, there is shown a use scenario for the control system 100 of Figure 2. In particular there is shown a room 300 (such as a garage) which the vehicle 10 is approaching to enter. It is to be appreciated that the room 300 of Figure 3 is for the purposes of illustration only, and that the present embodiments may be utilised in any appropriate area. Returning to Figure 3, the room 300 itself (comprising the area proximate to the vehicle 10) is typically poorly lit due to its enclosed nature. In the use scenario shown, partial illumination of the room 300 is provided by way of an exterior lighting system 20 of the vehicle 10 (e.g., headlights ofthe vehicle 10). However, due to the nature ofthe exterior lighting system 20, only a portion ofthe room 300 is illuminated, as illustrated by the two illuminated areas 310. This will typically not be sufficient to permit the use, or full functionality, of driver assistance systems 40 ofthe vehicle 10, which may require image data ofthe room 300 (captured by the one or more cameras 30 ofthe vehicle 10) where the whole room 300 is illuminated. By way of example, the scenario of Figure 3 shows two objects 320 which are not fully illuminated by the exterior lighting system 20. As such, any image data captured by the one or more cameras 30 may not accurately indicate the position and dimension ofthe objects 320, and consequently can lead to improper operation ofthe driver assistance systems 40. In embodiments ofthe present invention, this limitation is overcome by detection of under-illumination within image data ofthe room 300 captured by one or more cameras 30 ofthe vehicle 10 (typically by either the one or more cameras 30, or by a vehicle processor 130 in accordance with embodiments described above). An indication of this detection is then provided to the control system 100. The control system 100 then provides an instruction to the exterior lighting system 20 to illuminate the area proximate to the vehicle 10, such that the one or more cameras 30 are able to capture images ofthe area when it is sufficiently illuminated. In the use scenario of Figure 3, such instruction comprises instructing adaptive headlights ofthe vehicle 10 to perform a sweep ofthe room 300, causing the two illuminated areas 310 to pan across the room 300 (as indicated by the arrows). This sweep may cause the illuminated areas 310 to move only horizontally, only vertically, or in some embodiments both horizontally and vertically in accordance with the requirements of the driver assistance systems 40. The one or more cameras 30 may then be configured to capture images of each illuminated area 310 as the illuminated areas 310 pan across the room 300. In this manner, image data may be obtained ofthe entire room 300 in a sufficiently illuminated state to enable use of driver assistance systems 40. The control system 100 is then provided with the image data provided in each ofthe captured images and subsequently generates a volumetric reconstruction ofthe illuminated area proximate to the vehicle 10 based upon the captured images and image data. The volumetric reconstruction provides a three dimensional model ofthe illuminated area which enables the generation of views from a plurality of positions from within the three dimensional model. In some embodiments, the volumetric reconstruction may then be provided to, and utilised by, one or more driver assistance systems 40 of the vehicle 10. This will typically replace image data which would usually be utilised by the driver assistance systems 40 in order to achieve their functionality (e.g., to generate views of the exterior of the vehicle 10 in the case of visualisation systems, or to manoeuvre the vehicle 10 around the area proximate to the vehicle 10 in the case of autonomous drive systems). In low lighting conditions such as the one illustrated in Figure 3, the use of a volumetric reconstruction may be advantageous over the use of image data alone. In particular, driver assistance systems 40 may be configured to be used over a continuous time period, during which the vehicle 10 may move position. For example, where the driver assistance system 40 comprises an autonomous parking system, the position of the vehicle 10 may be controlled by the autonomous parking system to park the vehicle 10 in an appropriate position. Typically, an autonomous parking system will use image data of the exterior of the vehicle 10 to determine an appropriate position for the vehicle 10 to be parked, and to navigate the vehicle 10 to this position whilst avoiding obstacles in the surrounding area. In order to ensure the vehicle 10 is moved in an appropriate manner, the autonomous parking system may require a continuous stream of sufficiently illuminated image data of the area in which the vehicle 10 is being moved. If only image data were to be used in this scenario, this may then require the frequent re-illumination of the room 300 (to obtain new illuminated image data) in accordance with embodiments described above. By utilising the volumetric reconstruction, the autonomous parking system may instead continuously generate and update simulated views within the volumetric reconstruction based on an estimated position of the vehicle 10. This advantageously only necessitates one instance of image capture. In some embodiments, the control system 100 may be configured to update the volumetric reconstruction of the illuminated area proximate to the vehicle 10 based on positional data of the vehicle 10. In such embodiments, the control system 100 may receive the positional data from a navigational system of the vehicle 10. These embodiments may be used in conjunction with, or independently of, embodiments in which the volumetric reconstruction is provided to a driver assistance system 40 of the vehicle 10. In some embodiments, the estimated position of the vehicle 10 may be based on a known initial position of the vehicle 10 and the speed of the vehicle 10, wherein the speed of the vehicle 10 is similarly provided by an appropriate system of the vehicle 10. It is to be appreciated that whilst the above example has been described with respect to an autonomous parking system, the driver assistance system 40 may comprise any suitable system. These include, but are not limited to, a visualisation system on a display of the vehicle 10, a steering assist functionality, and an automatic braking functionality. The volumetric reconstruction may be obtained by execution of a volumetric reconstruction algorithm by the control system 100. Any form of volumetric reconstruction algorithm may be used which enables the functionality described herein. One example of such an algorithm is a Neural Radiance Field (NeRF) algorithm in which the captured images are used to represent the area proximate to the vehicle 10 as a radiance field. In some embodiments, a plurality of images are provided to the algorithm in which each of the images provides a separate viewing angle of the area proximate to the vehicle 10. The radiance field is parameterised by appropriate training of a neural network. In particular, the neural network is trained to predict emitted radiance at a particular location based upon a viewing angle of the location. A plurality of points within the area to be reconstructed are sampled and based upon this sampling, a volumetric reconstruction is rendered. Further information regarding NeRF algorithms may be found in “NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis” (Mildenhall et al, 03 August 2020). In some embodiments in which a NeRF algorithm is used, the neural network may be conditioned on the illumination exposure of the image, thereby enabling an accurate volumetric reconstruction to be generated even where the illumination level differs between images. Such conditioning may be achieved by providing a level of exposure in the captured images as a variable training input for the NeRF algorithm (or any other suitable volumetric reconstruction algorithm), where the level of exposure may be expressed as a value which is determined either by the one or more cameras 30, the vehicle processor 130 (or any other suitably configured vehicle system), or by the control system 100. This enables a volumetric reconstruction to be generated where the level of illumination within the reconstruction is controllable by the control system 100. This for instance may enable a volumetric reconstruction to be generated where the level of illumination is uniform, even where the illumination in the captured images is not. Another example of a suitable volumetric reconstruction algorithm is 3D Gaussian Splatting (examples of which can be found at https: / / repo-sam.inria.fr / fungraph / 3d-gaussian-splatting / ). It is to be appreciated that the two examples provided are for illustrative purposes only, and that any suitable volumetric algorithm may be used which achieves the functionality described herein. In some embodiments, each camera 30 of the one or more cameras 30 may be configured to capture a plurality of images (i.e. each camera 30 of the one or more cameras 30 captures a set of multiple images). The control system 100 may be configured to merge the received illuminated captured images for each camera 30 of the one or more cameras 30 to generate a single merged image of the illuminated area for every camera 30. This single merged image for every camera 30 may then be used to generate the volumetric reconstruction. In some instances, this may advantageously improve the training of the volumetric reconstruction algorithm and / or improve the accuracy of the generated volumetric reconstruction. The illuminated captured images in some embodiments may capture image data of an overlapping common region of the area proximate to the vehicle 10. In some embodiments, the control system 100 may be configured to identify the image data representative of the common region and subsequently select the image data which has the highest illumination of the common region when generating the single merged image for every camera 30. In additional embodiments, before a volumetric reconstruction is generated, the control system 100 may be configured to merge the received illuminated captured images to generate a single merged image of the illuminated area. This single merged image may then be used to generate the volumetric reconstruction. In some instances, this may advantageously improve the training of the volumetric reconstruction algorithm and / or improve the accuracy of the generated volumetric reconstruction. The illuminated captured images in some embodiments may capture image data of an overlapping common region of the area proximate to the vehicle 10. In some embodiments, the control system 100 may be configured to identify the image data representative of the common region and subsequently select the image data which has the highest illumination of the common region when generating the single merged image. The control system 100 may also be configured to ensure that the vehicle 10 is slowed or brought to a stop prior to the instruction being sent to the exterior lighting system 20 to illuminate the area proximate to the vehicle 10. This may be achieved by the control system 100 being configured to, upon receipt of the indication of detection of under-illumination within image data of the area proximate to the vehicle 10, instructing a torque system of the vehicle 10 to slow or stop the vehicle 10. This may help to enhance the accuracy of the volumetric reconstruction by ensuring that the position of the vehicle 10 is more precisely known at the time of image capture. This may also help to increase the quality of the captured images by reducing the chance of blurring due to vehicle 10 movement. In some embodiments, the process of instruction to the exterior lighting system 20 to illuminate the area proximate to the vehicle 10, and capture of images of the illuminated area proximate to the vehicle 10 may be continuous until an instruction to cease is provided by the control system 100. Similarly, generation of the volumetric reconstruction may also be continuous such that the initially generated volumetric reconstruction is updated in accordance with newly captured images of the illuminated area proximate to the vehicle 10. In such an embodiment, following the initial indication that one or more images is under illuminated, the control system 100 may be configured to instruct the exterior lighting system 20 to continually illuminate the area proximate to the vehicle 10 (e.g. by instructing adaptive headlights of the vehicle 10 to perform continual sweeps of the area) and to receive a plurality of sets of images of the area, where the sets of image correspond to images of the area where the vehicle 10 is at a particular location. The images may be configured to be taken on a periodic basis. For each set of images, the control system 100 may be configured to generate a new (updated) volumetric reconstruction. Such an embodiment may be advantageous in instances where the vehicle 10 is in motion and / or where the area proximate to the vehicle 10 comprises moving elements whose position may change and therefore may not be accurately reflected in the initial image. Such an embodiment may be configured to be used when a vehicle 10 is travelling at a low speed e.g. between 0 and 5 miles per hour. Figure 4 illustrates a method 400 according to an embodiment of the invention. The method 400 is a method of controlling a vehicle 10, such as the vehicle 10 illustrated in Figure 1. In particular, the method 400 is a method of controlling an exterior lighting system 20 of the vehicle 10 to illuminate an area proximate to the vehicle 10, and to subsequently generate a volumetric reconstruction of the area. The method 400 may be performed by the system 100 illustrated in Figure 2. In particular, the memory 130 may comprise computer-readable instructions which, when executed by the processor 120, perform the method 400 according to an embodiment of the invention. The method proceeds when the control system 100 receives, at Step 402, an indication that an image, captured by one or more cameras 30 of the vehicle 10, of an area proximate to the vehicle 10 is under-illuminated. The indication may be received directly from the one or more cameras 30, or from a vehicle processor 130 configured to receive the images captured by the one or more cameras 30 and perform the determination of whether the level of illumination in the captured images is under-illuminated in accordance with embodiments described above. Following receipt of the indication, the control system 100 then instructs, at Step 404, an exterior lighting system 20 of the vehicle 10 to illuminate the area proximate to the vehicle 10. The illumination of the area may be achieved in accordance with the embodiments described above. In particular, in some embodiments the exterior lighting system 20 may comprise adaptive headlights of the vehicle 10, and the instruction from the control system 100 comprises the adaptive headlights performing a sweep of the area in order to illuminate portions of the area in sequence. In other embodiments, the exterior lighting system 20 may be configured to generate light such that the whole area is illuminated at once. The method 400 then proceeds by the control system 100 receiving, at Step 406, from the one or more cameras 30, a plurality of images of the illuminated area proximate to the vehicle 10. In particular, the one or more cameras 30 are configured to capture images of the area proximate to the vehicle 10 once the area has been illuminated as a result of the instruction by the control system 100 at Step 404. In embodiments in which portions of the area are lit sequentially by the exterior lighting system 20, the one or more cameras 30 may be configured to sequentially capture images only of the portion of the area which is illuminated. In embodiments in which the whole area is illuminated simultaneously, the one or more cameras 30 may be configured to capture images of the whole area simultaneously. After receipt of the plurality of images, the control system 100 then generates, at Step 408, a volumetric reconstruction of the illuminated area proximate to the vehicle 10 based on the received plurality of images. This may be performed by execution of a volumetric reconstruction algorithm in accordance with embodiments as described above. The generated volumetric reconstruction may then be used to generate simulated views of the area proximate to the vehicle 10 as described above. In some embodiments, the method 400 may also include the control system 100 being configured to instruct a torque system of the vehicle 10 to slow or stop the vehicle 10 following indication that one or more images of the area proximate to the vehicle 10 is underilluminated. Such an instruction would occur between Steps 402 and 404 of the method 400 of Figure 4, i.e., priorto instructing the exterior lighting system 20 to illuminate the area proximate to the vehicle 10. In some embodiments, the method 400 may further comprise the control system 100 being configured to merge the plurality of captured images of the illuminated area proximate to the vehicle 10. Such merging would occur between Steps 406 and 408 as described above. In further embodiments, the illuminated captured images in some embodiments may capture image data of an overlapping common region of the area proximate to the vehicle 10. In some embodiments, the control system 100 may be configured to identify the image data representative of the common region and subsequently select the image data which has the highest illumination of the common region when generating the single merged image. In accordance with embodiments described above, the merging of images may be performed individually for each camera 30 of the one or more cameras 30, in embodiments in which each camera 30 of the one or more cameras 30 is configured to provide a plurality of images. Further optionally, following the generation of the volumetric reconstruction at Step 408, the method 400 may also comprise provide the volumetric reconstruction to a driver assistance system 40 of the vehicle 10, such as a display system or an autonomous driving system. In some embodiments, the control system 100 may be configured such that, following Step 406, no volumetric reconstruction is created and instead, the images of the illuminated area are simply provided to a driver assistance system 40 of the vehicle 10. In some embodiments, the images, when provided, may first be merged in accordance with embodiments described herein. These may be provided to the driver assistance system 40 by the control system 100. Such an embodiment may advantageously enable driver assistance systems 40 to identify objects 320 within a room which were previously poorly illuminated and unidentifiable, without requiring the generation of a volumetric reconstruction. Such identification can enable the driver assistance system 40 to function correctly e.g., by moving the vehicle 10 whilst avoiding the identified objects. Referring to Figure 5, there is shown a further method of operation 500 in accordance with embodiments of the invention. The method 500 is a method of controlling a vehicle 10, such as the vehicle 10 illustrated in Figure 1. In particular, the method 500 is a method of updating a previously generated volumetric reconstruction of an area proximate to the vehicle 10, typically following an initial generation of a volumetric reconstruction in accordance with the method 400 of Figure 4. The method 500 may be performed by the system 100 illustrated in Figure 2. In particular, the memory 130 may comprise computer-readable instructions which, when executed by the processor 120, perform the method 500 according to an embodiment of the invention. The method 500 begins following generation of the volumetric reconstruction, as shown in Step 408 of Figure 4. In some embodiments, the control system 100 may be configured to receive the volumetric reconstruction from another source. The volumetric reconstruction comprises a representation of the area proximate to the vehicle 10, where the reconstruction has been generated based upon an initial position of the vehicle 10 and views which are generated being simulated from a position within the volumetric reconstruction which is equivalent to a corresponding position of the vehicle 10 in the physical area. When the vehicle 10 changes position, it may be necessary to update the volumetric reconstruction (or equivalently, views generated by the volumetric reconstruction), based upon the updated position. As a result, following the generation of the volumetric reconstruction, the control signal is configured to receive, at Step 502, positional data of the vehicle 10 from a navigational system of the vehicle 10. This positional data is received where, following receipt of the initial volumetric reconstruction, the vehicle 10 has now changed positions. This may be as a result of an action of a driver assistance system 40 (such as an autonomous drive system as described in embodiments above), or otherwise. Once the positional data is received, the method 500 continues by the control system 100 updating based on the received positional data, at Step 504, the volumetric reconstruction of the illuminated area proximate to the vehicle 10. This may comprise generating new simulated views from within the volumetric reconstruction based on the illuminated captured images originally provided when generating the volumetric reconstruction, with the 5 simulated view being generated from a point of origin within the volumetric reconstruction which is equivalent to the positional data of the vehicle 10 in the physical area. It is to be appreciated that the method 500 illustrated in Figure 5 may be configured to be performed continuously i.e., for each time the vehicle 10 moves and positional data is provided, the method 500 may be 10 enacted. In some embodiments, the volumetric reconstruction may only be updated where the positional data which is provided indicates that the vehicle 10 has moved from its previous position above a predetermined threshold amount. It will be appreciated that various changes and modifications can be made to the present invention without 15 departing from the scope of the present application.

Claims

1. A control system for use in a vehicle, the control system comprising one or more processors collectively configured to:receive an indication that an image, captured by one or more cameras of the vehicle, of an area proximate to the vehicle is under-illuminated;upon receipt of the indication, instruct an exterior lighting system of the vehicle to illuminate the area proximate to the vehicle;receive, from the one or more cameras, a plurality of images of the illuminated area proximate to the vehicle; andgenerate, based on the plurality of images of the illuminated area, a volumetric reconstruction of the illuminated area proximate to the vehicle.

2. The control system of Claim 1, wherein the one or more processors are collectively configured to, upon receipt of the indication, instruct a torque system of the vehicle to slow or stop the vehicle prior to instructing the exterior lighting system to illuminate the area proximate to the vehicle.

3. The control system of any previous claim, wherein the one or more processors are collectively configured to:render a view of the illuminated area based on the volumetric reconstruction of the illuminated area;receive positional data of the vehicle from a navigational system of the vehicle; andgenerate, based on the received positional data and the volumetric reconstruction of the illuminated area, a second view of the illuminated area proximate to the vehicle.

4. The control system of any previous claim, wherein the one or more processors are collectively configured to:upon receipt of the indication, instruct an exterior lighting system of the vehicle to continuously illuminate the area proximate to the vehicle over a time period;receive, from the one or more cameras, a continuous stream of a plurality of images of the illuminated area proximate to the vehicle over the time period; andupdate, based on a plurality of images of the illuminated area received subsequent to the generation of the volumetric reconstruction of the illuminated area proximate to the vehicle, the generated volumetric reconstruction of the illuminated area proximate to the vehicle.

5. The control system of any previous claim, wherein the plurality of images comprises one or more sets of multiple images, each set of multiple images being captured by a camera of the one or more cameras and the one or more processors are collectively configured to generate a single merged image for each camera of the one or more cameras by merging the set of multiple images captured by the corresponding camera.

6. The control system of Claim 5, wherein the one or more processors are collectively configured to, for each set of images:identify, from the set of multiple images, two or more images each comprising respective image data representative of a common region of the illuminated area;select the respective image data having a highest illumination of the common region; andgenerate the single merged image using, for the common region, the respective image data having the highest illumination.

7. The control system of any previous claim, wherein the exterior lighting system comprises one or more adaptive headlights of the vehicle, and the one or more processors are collectively configured to instruct the one or more adaptive headlights to illuminate the area proximate to the vehicle by instructing the adaptive headlights to perform a sweep of the area proximate to the vehicle.

8. The control system of Claim 7, wherein the sweep of the adaptive headlights sweeps through a 180° arc.

9. The control system of any previous claim, wherein the one or more processors are collectively configured to provide the volumetric reconstruction to a display system of the vehicle for display to a vehicle occupant.

10. The control system of any previous claim, wherein the one or more processors are collectively configured to provide the volumetric reconstruction as input data to an autonomous drive system of the vehicle.

11. The control system of any previous claim, wherein the one or more processors are collectively configured to generate the volumetric reconstruction using a Neural Radiance Field, NeRF, algorithm.

12. The control system of Claim 11, wherein the NeRF algorithm is conditioned based on the exposure of the plurality of images of the illuminated area proximate to the vehicle.

13. A vehicle, the vehicle comprising:one or more cameras;an exterior lighting system; andthe control system of any previous claim.

14. The vehicle of Claim 13, the vehicle further comprising an autonomous parking system, wherein the autonomous parking system is configured to:control a position of the vehicle based on the volumetric reconstruction of the illuminated area proximate to the vehicle; andprovide an indication of the position of the vehicle to the control system, andwherein the control system is configured to update the volumetric reconstruction of the illuminated area proximate to the vehicle based on the indication of the position of the vehicle.

15. A method for controlling a vehicle, the method comprising:receiving, at a control system of the vehicle, an indication that an image, captured by one or more cameras of the vehicle, of an area proximate to the vehicle is under-illuminated;upon receipt of the indication, instructing, by the control system, an exterior lighting system of the vehicle to illuminate the area proximate to the vehicle;5 receiving, at the control system from the one or more cameras, a plurality of images of the illuminatedarea proximate to the vehicle; andgenerating, based on the plurality of images of the illuminated area, a volumetric reconstruction of the illuminated area proximate to the vehicle.

Images