KR-20260062134-A - System for measuring three-dimensions of delivery goods automatically from low quality Image without depth information

KR20260062134AKR 20260062134 AKR20260062134 AKR 20260062134AKR-20260062134-A

Abstract

The single-image-based automatic volume measurement system for parcels without depth information according to the present invention includes: a Salient Object Detection (SOD) module that detects objects of parcels from customer verification images of parcels collected at a parcel logistics site; a Corner Detection (CD) module that searches for corners in the objects of parcels detected by the SOD module; and an Object Measurement (OM) module that derives three-dimensional dimensions using the corners in the objects of parcels searched by the CD module. Accordingly, it is possible to measure the three-dimensional dimensions of a parcel from a single black-and-white image that does not contain low-resolution depth information, and by utilizing existing infrastructure, it has the advantage of reducing costs and facilitating the dissemination and expansion of the system.

Inventors

김준
김다윗
김보현

Assignees

한국생산기술연구원

Dates

Publication Date: 20260507
Application Date: 20241025

Claims (17)

SOD (Salient Object Detection) module for detecting objects of said parcels from customer verification images of said parcels collected at a parcel logistics site; A CD (Corner Detection) module that searches for corners in the object of the parcel detected by the SOD module; and A single-image-based automatic volume measurement system for parcels without depth information, comprising an Object Measurement (OM) module that derives three-dimensional dimensions using corners in the object of the parcel found by the CD module.
In paragraph 1, The above SOD module is, An image enhancement module that adjusts the overall image illumination by calculating the difference in the ratio of illumination at a specific pixel location and the illumination near that pixel location in the customer verification image of the above-mentioned courier shipment; and A single-image-based automatic volume measurement system for parcels without depth information, comprising an ROI extraction module that recognizes an object of the parcel from an image improved by the image enhancement module and extracts the ROI area of the parcel.
In paragraph 2, The above image enhancement module is a single-image-based automatic parcel volume measurement system without depth information, implemented by a Single-Scale Retinex (SSR) algorithm applied through the operation of Mathematical Formula 1 below. [Mathematical Formula 1] Here, (x, y) represents the pixel coordinate location, R SSR (x, y) represents the image with the SSR algorithm applied, I(x, y) represents the original image, and G(x, y) represents the Gaussian filter.
In paragraph 2, The above ROI extraction module is implemented with the SOS (Salient Object Segmentation) algorithm, and a single image-based automatic parcel volume measurement system without depth information applies U2-Net, a deep learning model specialized in extracting high-resolution features among the SOS algorithms, capable of separating and extracting a specific object region of an image from the background.
In paragraph 2, The above CD module is a single-image-based automatic parcel volume measurement system without depth information that searches for corner points among pixels on the outline in the ROI area of the parcel extracted by the above ROI extraction module.
In paragraph 5, The above CD module is a single-image-based automatic parcel volume measurement system without depth information, implemented by an LPD-CD (Line-to-Point Distance-based Corner Detection) algorithm that defines curvature based on the vertical distance between a point on a straight line and a point on a curve, based on a triangle formed by a straight line connecting two endpoints located at a specific range from the center of each curve on the outline of the ROI area of the parcel having multiple curved regions, and selects the case where the vertical distance is maximum as a corner point.
In paragraph 6, The above LPD-CD algorithm is a single-image-based automatic parcel volume measurement system without depth information that defines the relative position of a pixel corresponding to a corner point so that the OM module measures dimensions based on the distance between pixels.
In paragraph 1, The above OM module defines the projection relationship between corner pixels and real-world coordinates in the object of the parcel searched by the above CD module using a neural network-based learning technique, and derives the 3D dimensions of the parcel based on a single image without depth information by estimating the real-world length corresponding to the distance between pixels through the output variables of three neural network models.
A step of detecting an object of the said courier shipment from a customer proof image of the courier shipment collected at a courier logistics site; A step of searching for corners in the object of the detected courier shipment; and A control method for a single-image-based automatic volume measurement system for parcels without depth information, comprising the step of deriving three-dimensional dimensions using corners in the object of the parcel found above.
In Paragraph 9, The step of detecting the object of the above-mentioned courier shipment is, A step of adjusting the overall image illumination by calculating the difference in the ratio of illumination at a specific pixel location and the illumination near the said pixel location in the customer proof image of the above-mentioned courier shipment; and A control method for a single-image-based automatic volume measurement system for a parcel without depth information, comprising the step of recognizing an object of the parcel from an image with adjusted image illumination and extracting an ROI area of the parcel.
In Paragraph 10, A control method for a single-image-based automatic parcel volume measurement system without depth information, comprising a step of adjusting the image illumination, which is implemented by a Single-Scale Retinex (SSR) algorithm applied through the operation of the following mathematical formula 1. [Mathematical Formula 1] Here, (x, y) represents the pixel coordinate location, R SSR (x, y) represents the image with the SSR algorithm applied, I(x, y) represents the original image, and G(x, y) represents the Gaussian filter.
In Paragraph 10, A control method for a single-image-based automatic parcel volume measurement system without depth information, comprising the step of applying U2-Net, which is a deep learning model specialized in extracting high-resolution features among the SOS algorithms and capable of separating and extracting a specific object region of an image from the background, wherein the step of extracting the ROI region is implemented using a Salient Object Segmentation (SOS) algorithm.
In Paragraph 10, A control method for a single-image-based automatic volume measurement system for parcels without depth information, comprising the step of searching for corners, which includes the step of searching for points corresponding to corners among pixels on the outline in the ROI area of the parcel.
In Paragraph 13, A control method for a single-image-based automatic parcel volume measurement system without depth information, comprising the step of detecting the corner, which is implemented by an LPD-CD (Line-to-Point Distance-based Corner Detection) algorithm that defines curvature based on the vertical distance between a point on a straight line and a point on a curve, based on a triangle formed by a straight line connecting two endpoints located at a specific range from the center of each curve on the outline of the ROI area of the parcel having multiple curved regions, and selects the case where the vertical distance is maximum as the corner point.
In Paragraph 14, The above LPD-CD algorithm is a control method for a single-image-based automatic parcel volume measurement system without depth information, comprising the step of defining a relative position for a pixel corresponding to the corner point.
In Paragraph 9, A control method for a single-image-based automatic volume measurement system for a parcel without depth information, comprising the step of deriving the above-mentioned three-dimensional dimensions, defining the projection relationship between corner pixels and real-world coordinates in the object of the parcel using a neural network-based learning technique, and deriving the three-dimensional dimensions of the parcel by estimating the real-world length corresponding to the distance between pixels through the output variables of three neural network models.
A computer-readable recording medium having a program recorded thereon for performing the method of any one of paragraphs 9 through 16.

Description

System for automatically measuring the volume of delivery goods based on a single image without depth information and method for controlling the same The present invention relates to a single-image-based automatic volume measurement system for parcels without depth information and a control method thereof. More specifically, it relates to a single-image-based automatic volume measurement system for parcels without depth information and a control method thereof that enables three-dimensional dimension measurement of parcels from a single black-and-white image that does not contain depth information and reduces costs by utilizing existing infrastructure and facilitates the dissemination and expansion of the system. As the size of the online market expands due to the recent growth of e-commerce, the demand for delivery of various consumer products is increasing. Consequently, the importance of the courier industry is growing, and its scale is also expanding. Courier companies are employing strategies such as optimizing delivery routes, introducing electric vehicles, and diversifying delivery methods based on cargo characteristics to maximize profits through the provision of efficient delivery services. In particular, recently, when setting freight rate standards, they are attempting to further subdivide rates by additionally incorporating information on cargo size and volume, in addition to the weight of the parcel that was previously considered. In order to utilize information on the size and volume of parcel shipments as a basis for determining freight rates, it is necessary to automate the measurement of shipment volume. To this end, high-performance sensor-based equipment for measuring the three-dimensional dimensions of shipments is being developed, but commercialization and field application are difficult due to the high cost of introducing the equipment. Figure 1 is an example of an image for customer verification of a parcel collected at a general parcel logistics site. FIG. 2 shows a block diagram of a single-image-based automatic parcel volume measurement system without depth information according to an embodiment of the present invention. FIG. 3 is a diagram for comparing an original image and an image to which an SSR algorithm has been applied according to an embodiment of the present invention. FIG. 4 is a diagram for comparing an original image and an image to which the SOS algorithm has been applied, according to an embodiment of the present invention. FIG. 5 is an example diagram of the relative position definition of pixels corresponding to major corners in the outline of a courier package according to one embodiment of the present invention. FIG. 6 is a diagram illustrating the curvature estimation scale defined in the LPD-CD algorithm according to one embodiment of the present invention. FIG. 7 is a diagram illustrating the operating principle of the LPD-CD algorithm according to one embodiment of the present invention. FIG. 8 is an example of an implementation of the LPD-CD algorithm according to one embodiment of the present invention. FIG. 9 is a diagram for comparing an original image and a corner image detected after applying a CD module according to an embodiment of the present invention. FIG. 10 is a control flow diagram of a single image-based automatic parcel volume measurement system without depth information according to an embodiment of the present invention. The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various other forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the claims. Throughout the specification, the same reference numerals refer to the same components. Throughout the specification, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as "...part," "...unit," and "module" as used in the specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware, software, or a combination of hardware and software. Additionally, terms such as "first," "second," etc., may be used to describe various components, but said components should not be limited by said terms. With reference to the attached drawings, a single-image-based automatic volume measurement system for parcels without depth information and a control method thereof according to an embodiment of the present invention will be described below. At this point, it wi