CN-122029577-A - Volume sensing using container monitoring system

Abstract

Methods, apparatus, systems, devices, and computer program products for volume sensing using container monitoring systems are disclosed. In certain embodiments, the cargo monitoring system captures a first set of images of a dock scene through a stereoscopic vision system of a dock-mounted monitoring device. The cargo monitoring system calibrates a stereoscopic vision system of the dock-mounted monitoring device based on the first set of images. The container monitoring system determines positioning parameters of a quay-mounted monitoring device relative to a container in a quay scene based on the first set of images. The container monitoring system generates a disparity map of a dock scene based on the first set of images. The container monitoring system generates a depth map of the container interior based on the disparity map and the positioning parameters.

Inventors

• B. J. Wollstone

Assignees

• 智能见证美国有限责任公司

Dates

Publication Date

20260512

Application Date

20230817

Claims (20)

1. 1. A method of volume sensing using a container monitoring system, the method comprising: a dock sensing controller of the container monitoring system utilizing a first set of images of a dock scene captured by a stereoscopic vision system of the container monitoring system; The dock sensing controller determining positioning parameters of a dock-mounted monitoring device relative to a container in a dock scene based on a first set of images; the dock sensing controller generating a depth map of an interior space of the container based on the positioning parameters and a first set of images, and The dock sensing controller generates a cargo map of the container based on the depth map and cargo estimates from a second set of images.
2. 2. The method of claim 1, wherein the stereoscopic vision system comprises at least a first camera and a second camera, and wherein the disparity map comprises a pixel offset of each pixel in a first image captured by the first camera relative to a second image captured by the second camera.
3. 3. The method of claim 1, wherein the dock-mounted monitoring device is mounted in a fixed location on the dock.
4. 4. A method according to claim 3, wherein the container is a trailer parked at a dock.
5. 5. The method of claim 1, further comprising: The dock sensing controller captures a first set of images of a dock scene through the stereoscopic vision system.
6. 6. The method of claim 1, further comprising: the trained machine learning classifier of the container monitoring system detects that a door of the container is open.
7. 7. The method of claim 1, further comprising: a loading event is detected based at least on the infrared sensor data.
8. 8. The method of claim 1, wherein the dock sensing controller generating a cargo map of the container based on the depth map and cargo estimates from a second set of images comprises: Capturing a second set of images of the dock scene, and A scene change of the interior space of the container is detected.
9. 9. The method of claim 1, further comprising: And classifying the occupancy rate of the container.
10. 10. The method of claim 1, further comprising: Detecting a loading inefficiency in the container.
11. 11. The method of claim 10, wherein the inefficiency of loading is based on a distance between the first cargo item and the second cargo item.
12. 12. The method of claim 1, further comprising: and displaying the cargo graph to a user.
13. 13. An apparatus for volume sensing using a container monitoring system, the apparatus comprising: Processor, and A memory storing instructions that, when executed by a processor, cause the apparatus to: a dock sensing controller of the container monitoring system utilizing a first set of images of a dock scene captured by a stereoscopic vision system of the container monitoring system; The dock sensing controller determining positioning parameters of a dock-mounted monitoring device relative to a container in a dock scene based on a first set of images; the dock sensing controller generating a depth map of an interior space of the container based on the positioning parameters and a first set of images, and The dock sensing controller generates a cargo map of the container based on the depth map and cargo estimates from a second set of images.
14. 14. The apparatus of claim 13, wherein the stereoscopic vision system comprises at least a first camera and a second camera, and wherein the disparity map comprises a pixel offset of each pixel in a first image captured by the first camera relative to a second image captured by the second camera.
15. 15. The apparatus of claim 13, wherein the dock-mounted monitoring device is mounted in a fixed location on the dock.
16. 16. The apparatus of claim 13, further comprising instructions that when executed by the processor cause the apparatus to perform: A door of the container is detected as open by a trained machine learning classifier of the container monitoring system.
17. 17. The apparatus of claim 13, further comprising instructions that when executed by the processor cause the apparatus to perform: a loading event is detected based at least on the infrared sensor data.
18. 18. The apparatus of claim 13, further comprising instructions that when executed by the processor cause the apparatus to perform: and displaying the cargo image to a user through the wharf sensing controller.
19. 19. The apparatus of claim 13, further comprising instructions that when executed by the processor cause the apparatus to perform: And classifying the occupancy rate of the container.
20. 20. The apparatus of claim 13, further comprising instructions that when executed by the processor cause the apparatus to perform: Detecting a loading inefficiency in the container.

Description

Volume sensing using container monitoring system Background Cargo shipment and transportation is one of the main life lines of society, facilitating efficient long distance transport of cargo. For example, a company may load a product into a cargo container for transportation using a tractor, train, ship, or the like. In order to minimize the high cost of such transportation, cargo containers should be packed as efficiently as possible. However, it may be difficult for dock personnel to accurately determine the remaining capacity of the cargo container when loading the container. Also, when cargo items are inefficiently placed in a container, identification may be difficult, thereby reducing the amount of cargo that the container will hold. Light detection and ranging (LiDAR) may be used to obtain depth measurements for volume sensing to estimate occupancy of cargo within a container. However, liDAR systems are very expensive and difficult to maintain calibration. Active light can lose depth accuracy in the presence of ambient light and, therefore, dock lighting can degrade system performance. In addition, cargo sensors of trailers require long-range depth measurements. The standard trailer is 53 feet and the apparatus can be installed behind the door, thus requiring depth measurements above 60 feet. The remote LiDAR system presents safety concerns because it may require a high power laser as the active light source, which may cause eye damage to nearby personnel. Disclosure of Invention Methods, apparatus, systems, devices, and computer program products for volume sensing using container monitoring systems are disclosed. In certain embodiments, the dock sensing controller performs volume sensing of the cargo container using images captured by the dock-mounted monitoring device. The dock-mounted monitoring device includes a depth camera implemented by a stereoscopic vision system comprising two monocular cameras. Stereoscopic vision systems are safer and less costly than LiDAR systems. Furthermore, the stereoscopic vision system is self-calibrating. The dock sensing controller is self-locating such that the orientation of the dock mounted monitoring device relative to the moored container is continuously determined by machine vision and feature extraction. In some examples, a trained object detector is used to distinguish between a fully loaded container and a container with a closed door. In some implementations, the dock sensing controller also uses the object detector to classify the container as empty. When the container is empty, the dock sensing controller generates a depth map of the container from the volumetric sensing data. When cargo is loaded into a container, the terminal sense controller generates a cargo map and reports the occupancy of the container (i.e., the full load of the container). The infrared sensor may be used to identify the time period of loading or unloading. The dock sensing controller may further detect and report loading inefficiencies, such as gaps between pallets, crates, or other cargo items. In a particular embodiment, the dock sensing controller utilizes a first set of images of a dock scene captured from a stereoscopic vision system of the container monitoring system. The dock sensing controller determines a positioning parameter of the dock mounted monitoring device relative to a container in the dock scene based on the first set of images. The dock sensing controller generates a depth map of the interior space of the container based on the positioning parameters and the first set of images. When the dock sensing controller captures a set of updated images, the dock sensing sensor may identify a change in a dock scene associated with an interior space of the container, wherein the change in the dock scene indicates the presence of the cargo. The dock sensing controller generates a cargo map of the container based on the depth map and the cargo estimate from the second set of images. The foregoing and other objects, features and advantages of the invention will be apparent from the following more particular descriptions of exemplary embodiments of the invention as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts of exemplary embodiments of the invention. Drawings FIG. 1 illustrates a schematic diagram of a dock scenario of a container monitoring system suitable for volume sensing using the container monitoring system in accordance with at least one embodiment of the present disclosure; FIG. 2 illustrates a block diagram of a container monitoring system for volume sensing using the container monitoring system in accordance with at least one embodiment of the present disclosure; FIG. 3 is a flow chart illustrating an implementation of a method for volume sensing using a container monitoring system in accordance with at least one embodiment of the present disclosure; FIG. 4 is a flow chart illustrating yet another imple