105 are typically implemented by virtual computing environments that run on various computers making up the computers of host physical machine set 142, which is the universe of physical computers in and/or available to public cloud 105. The virtual computing environments (VCEs) typically take the form of virtual machines from virtual machine set 143 and/or containers from container set 144. It is understood that these VCEs may be stored as images and may be transferred among and between the various physical machine hosts, either as images or after instantiation of the VCE. Cloud orchestration module 141 manages the transfer and storage of images, deploys new instantiations of VCEs and manages active instantiations of VCE deployments. Gateway 140 is the collection of computer software, hardware, and firmware that allows public cloud 105 to communicate through WAN 102.

Some further explanation of virtualized computing environments (VCEs) will now be provided. VCEs can be stored as “images.” A new active instance of the VCE can be instantiated from the image. Two familiar types of VCEs are virtual machines and containers. A container is a VCE that uses operating-system-level virtualization. This refers to an operating system feature in which the kernel allows the existence of multiple isolated user-space instances, called containers. These isolated user-space instances typically behave as real computers from the point of view of programs running in them. A computer program running on an ordinary operating system can utilize all resources of that computer, such as connected devices, files and folders, network shares, CPU power, and quantifiable hardware capabilities. However, programs running inside a container can only use the contents of the container and devices assigned to the container, a feature which is known as containerization.

Private cloud 106 is similar to public cloud 105, except that the computing resources are only available for use by a single enterprise. While private cloud 106 is depicted as being in communication with WAN 102, in other embodiments a private cloud may be disconnected from the internet entirely and only accessible through a local/private network. A hybrid cloud is a composition of multiple clouds of different types (for example, private, community or public cloud types), often respectively implemented by different vendors. Each of the multiple clouds remains a separate and discrete entity, but the larger hybrid cloud architecture is bound together by standardized or proprietary technology that enables orchestration, management, and/or data/application portability between the multiple constituent clouds. In this embodiment, public cloud 105 and private cloud 106 are both part of a larger hybrid cloud.

According to the present embodiment, a user using any combination of an EUD 103, remote server 104, public cloud 105, and private cloud 106 may implement the brake detection program 150 to automatically detect a braking action of a first vehicle in front of a second vehicle, based on analyzing one or more geometric measurements of a rear portion of the first vehicle that have been captured in a sequence of images recorded by the second vehicle. Embodiments of the present disclosure are explained in more detail below with respect to FIGS. 2 to 5.

Referring now to FIG. 2, a schematic block diagram of an automotive safety environment 200 according to at least one embodiment is depicted. According to one embodiment, the automotive safety environment 200 may include a computer system 202 having a tangible storage device and a processor that is enabled to run the brake detection program 150.

According to one embodiment, the automotive safety environment 200 may include a first vehicle 204 (e.g., leading/preceding vehicle) traveling in front of a second vehicle 206 (e.g., trailing/following vehicle) on a road surface 208.

Generally, the computer system 202 may be enabled by the brake detection program 150 to detect a velocity gradient (e.g., braking/deceleration intensity) of the first vehicle 204 based on a set of images 210 (e.g., sequential images; sequential image data) of a rear view of the first vehicle 204, as recorded by a camera 212 associated with the second vehicle 206.

According to one embodiment, the computer system 202 may include one or more components (e.g., computer 101; end user device (EUD) 103; WAN 102) of the computer environment 100 described above with reference to FIG. 1. In one embodiment, the computer system 202 may include one or more computers (e.g., computer 101) which may take the form of a vehicle computer, desktop computer, laptop computer, tablet computer, smart phone, smart watch or other wearable computer, mainframe computer, quantum computer or any other form of computer or mobile device now known or to be developed in the future that is capable of running a program, accessing a network, and/or querying a database.

According to one embodiment, the computer system 202 may provide a vehicle computing device 214 associated with the second vehicle 206. Although vehicle computing device 214 is illustrated in FIG. 2 as an in-built computing device, various aspects of the vehicle computing device 214 may operate as a server (e.g., remote server 104) in a client-server model. Further, aspects of the computer system 202 (e.g., including vehicle computing device 214) may operate in a cloud computing service model, such as Software as a Service (SaaS), Platform as a Service (PaaS), or Infrastructure as a Service (IaaS). In one embodiment, the computer system 202 may also be implemented as a cloud computing deployment model, such as a private cloud, community cloud, public cloud, or hybrid cloud.

In one embodiment, the brake detection program 150 may include a single computer program or multiple program modules or sets of instructions being executed by the processor of the computer system 202 (e.g., vehicle computing device 214). In one embodiment, the brake detection program 150 may include routines, objects, components, units, logic, data structures, and actions that may perform particular tasks or implement particular abstract data types. In one embodiment, the brake detection program 150 may be practiced in distributed cloud computing environments where tasks may be performed by local and/or remote processing devices which may be linked through a communication network (e.g., WAN 102). In at least one embodiment, the brake detection program 150 (e.g., the various modules) may be executed on a single computing device (e.g., vehicle computing device 214).

According to one embodiment, the brake detection program 150 may include at least the following modules: an image capture and analysis module 216, a geometric measurement module 218, a brake intensity module 220, a range and threshold module 222, and an intervention module 224. Each of these modules will be detailed further below with reference to FIGS. 2-4.

According to one embodiment, the image capture and analysis module 216 may implement the camera 212 of the second vehicle 206 to capture the set of images 210. In one embodiment, the set of images 210 may be recorded as continuous video and divided into sequential image frames. Thus, the set of images 210 may include a set of sequential images.

According to one embodiment, the set of images 210 captured by the camera 212 may include images of a rear view of the first vehicle 204. In one embodiment, the image capture and analysis module 216 may implement computer vision techniques to detect one or more objects in the set of images 210. In one embodiment, the image capture and analysis module 216 may detect a tail light object 226, rear vehicle surface object 228, and a road surface object 230 in each image of the set of images 210. The tail light object 226 may be an image of a set of tail lights 232 of the first vehicle 204 and may therefore be referred to as the set of tail lights in the image 210. The rear vehicle surface object 226 may be an image of a rear vehicle surface 234 (e.g., bumper) of the first vehicle 204 and may therefore be referred to as the rear vehicle surface (e.g., bumper) in the image 210. The road surface object 230 may be an image of the road surface 208 and may therefore be referred to as the road surface in the image 210.

Referring now to FIG. 3, a schematic block diagram 300 of a first sequential image data used by the brake detection program 150 in the automotive safety environment 200 according to at least one embodiment is depicted.

According to one embodiment, the set of images 210 captured by the camera 212 may include a first image 302 of the first vehicle 204 and a second image 304 of the first vehicle 204. In one embodiment, the image capture and analysis module 216 may detect the set of tail lights 226 in the first image 302 and the second image 304 of the first vehicle 204. The image capture and analysis module 216 may also detect the rear vehicle surface 228 (e.g., rear bumper) in the first image 302 and the second image 304 of the first vehicle 204. The image capture and analysis module 216 may further detect the road surface 230 in the first image 302 (e.g., first road surface) and the second image 304 (e.g., second road surface) of the first vehicle 204.

According to one embodiment, the brake detection program 150 may implement the geometric measurement module 218 to analyze the first image 302. The geometric measurement module 218 may be implemented to measure a first constant distance 306 (e.g., first geometric distance (a)) between the set of tail lights 226 of the first vehicle 204. The geometric measurement module 218 may also be implemented to measure a first variable distance 308 (e.g., second geometric distance (b)) between the rear vehicle surface 228 (e.g., bumper) on the rear portion of the first vehicle and 204 the road surface 230. In at least one embodiment, the first variable distance 308 may include a perpendicular distance (e.g., first perpendicular distance). Then, the brake detection program 150 may implement the geometric measurement module 218 to determine (e.g., calculate) a first geometric ratio 310 associated with the rear portion of the first vehicle 204, from the first image 302 (e.g., first ratio between the measured first constant distance 306 and the measured first variable distance 308). The first geometric ratio 310 associated with the first vehicle 204 may be calculated continuously while the first vehicle 204 and the second vehicle 206 are in motion.

Similarly, the brake detection program 150 may implement the geometric measurement module 218 to analyze the second image 304. The geometric measurement module 218 may be implemented to measure a second constant distance 312 (e.g., first geometric distance (a′)) between the set of tail lights 226 of the first vehicle 204. The geometric measurement module 218 may also be implemented to measure a second variable distance 314 (e.g., second geometric distance (b′)) between the rear vehicle surface 228 (e.g., bumper) on the rear portion of the first vehicle and 204 the road surface 230. In at least one embodiment, the second variable distance 314 may include a perpendicular distance (e.g., second perpendicular distance). Then, the brake detection program 150 may implement the geometric measurement module 218 to determine (e.g., calculate) a second geometric ratio 316 associated with the rear portion of the first vehicle 204, from the second image 304 (e.g., second ratio between the measured second constant distance 312 and the measured second variable distance 314). The second geometric ratio 316 associated with the first vehicle 204 may be calculated continuously while the first vehicle 204 and the second vehicle 206 are in motion.

According to one embodiment, the brake detection program 150 may implement the brake intensity module 220 to compare the first geometric ratio 310 and the second geometric ratio 316 from the respective sequential first and second images 302, 304. In one embodiment, the comparison between the first geometric ratio 310 and the second geometric ratio 316 from two consecutive images (e.g., first image 302; second image 304) may be performed continuously while the first vehicle 204 and the second vehicle 206 are in motion.

In one embodiment, if the brake intensity module 220 determines that the second geometric ratio 316 is equal to the first geometric ratio 310, then the brake intensity module 220 may detect that the first vehicle 204 is moving at a constant acceleration (e.g., first vehicle 204 is not decelerating/braking). However, if the brake intensity module 220 determines that the second geometric ratio 316 is less than the first geometric ratio 310, then the brake intensity module 220 may detect a braking action (e.g., deceleration) of the first vehicle 204.

If the first vehicle 204 is braking, the second frame may be similar to the second image 304 where the second variable distance 314 (e.g., second geometric distance (b′)) is illustrated to be proportionally greater than the first variable distance 308 (e.g., second geometric distance (b)) in the first image 302 (e.g., first frame). For example, as shown in FIG. 2, the second geometric ratio 316 (e.g., a′/b′=3.71) may be lower than the first geometric ratio 310 (e.g., a/b=4.83) since the physical distance corresponding to the second variable distance 314 (e.g., second geometric distance (b′)) has increased.

According to one embodiment, the brake intensity module 220 may also determine an intensity of the braking action of the first vehicle 204 based on calculating a difference (e.g., change/delta) between the first geometric ratio 310 and the second geometric ratio 316. In various embodiments, the brake intensity module 220 may determine that an increase in the change or delta between the first geometric ratio 310 and the second geometric ratio 316 may indicate a corresponding increase in the intensity of the braking action.