US-12620133-B2 - System and method of imaging

US12620133B2US 12620133 B2US12620133 B2US 12620133B2US-12620133-B2

Abstract

A system and method for extracting a full range hyperspectral data from one or more RGB images. The method encompasses pre-processing, the one or more RGB images. Further the method encompasses estimating, an illumination component associated with each pre-processed RGB image. The method thereafter comprises removing, the illumination component from the each pre-processed RGB image. Further the method encompasses tracking, a trajectory of pixel(s) over frame(s) associated with the each pre-processed RGB image. The method then leads to identifying, a position of the pixel(s) in one or more adjacent frames of the frame(s) based on a patch defined around said one or more pixels. Thereafter the method encompasses extracting, the full range hyperspectral data from the each pre-processed RGB image based on at least one of the removal of the illumination component, the trajectory of the pixel(s) and the position of the pixel(s).

Inventors

Raghuram Lanka
P. BALAKRISHNA REDDY
ARUN BANERJEE
Pradip GUPTA
Shubham BHARDWAJ
Shailesh Kumar
Santanu Dasgupta
Rahul BADHWAR
Kenny PAUL

Assignees

Jio Platforms Limited

Dates

Publication Date: 20260505
Application Date: 20210528
Priority Date: 20200530

Claims (14)

1 . A method for extracting a full range hyperspectral data from one or more RGB images, the method comprising: receiving, at a transceiver unit from one or more camera devices, one or more RGB images; pre-processing, by a processing unit, the one or more RGB images; estimating, by the processing unit, an illumination component associated with each pre-processed RGB image of the one or more pre-processed RGB images based on a first pre-trained dataset, wherein the first pre-trained dataset comprises a plurality of data trained based on a depth value associated with each object captured in each image of a plurality of RGB images; removing, by the processing unit, the illumination component from the each pre-processed RGB image; tracking, by the processing unit, a trajectory of one or more pixels over one or more frames associated with the each pre-processed RGB image based on an optical flow model; identifying, by the processing unit, a position of the one or more pixels in one or more adjacent frames of the one or more frames based on a patch defined around said one or more pixels; and extracting, by the processing unit, the full range hyperspectral data from the each pre-processed RGB image corresponding to the one or more RGB images based on at least one of the removal of the illumination component, the trajectory of the one or more pixels and the position of the one or more pixels.
2 . The method as claimed in claim 1 , wherein the pre-processing comprises at least of a resizing of the one or more RGB images, de-noising of the one or more RGB images and enhancing an image quality of the one or more RGB images.
3 . The method as claimed in claim 1 , wherein the one or more camera devices comprises one or more Micro-Electro-Mechanical Systems (MEMS).
4 . The method as claimed in claim 1 , wherein the one or more RGB images are received at the transceiver unit via a master node associated with the one or more camera devices.
5 . The method as claimed in claim 1 , wherein the extracting, by the processing unit, the full range hyperspectral data is further based on a second pre-trained dataset, and wherein the second pre-trained dataset comprises a plurality of data trained based on a frame by frame conversion of a plurality of RGB images to corresponding Hyperspectral level resolution.
6 . The method as claimed in claim 1 , wherein estimating, by the processing unit, an illumination component associated with each pre-processed RGB image further comprises: assigning, by the processing unit, a depth value to every RGB pixel associated with the each pre-processed RGB image based on the first pre-trained dataset, synthesizing, by the processing unit, one or more images of one or more-objects captured in the each pre-processed RGB image under one or more illumination conditions based on the depth value assigned to the every RGB pixel, and estimating, by the processing unit, the illumination component associated with the each pre-processed RGB image based on the synthesized one or more images of the one or more objects, wherein the illumination component is estimated on a pixel level scale.
7 . The method as claimed in claim 6 , wherein the estimating, by the processing unit, the illumination component is further based on one or more Artificial intelligence techniques.
8 . The method as claimed in claim 1 , the method comprises determining, by the processing unit, a target RGB value associated with the each pre-processed RGB image under an ideal condition based on: removing, by the processing unit, the illumination component from the each pre-processed RGB image, retrieving, by the processing unit, an original RGB pixel value of one or more pixels of the each pre-processed RGB image based on the removal of the illumination component, and determining, by the processing unit, the target RGB value based on the original RGB pixel value of the one or more pixels of the each pre-processed RGB image.
9 . The method as claimed in claim 1 , the method further comprises performing by the processing unit, a pixel-level semantic segmentation on an object of interest present in the full range hyperspectral data corresponding to each RGB image of the one or more RGB images.
10 . The method as claimed in claim 9 , wherein the pixel-level semantic segmentation is performed based on one or more Artificial intelligence techniques.
11 . The method as claimed in claim 9 , the method further comprises: organising, by the processing unit, the full range hyperspectral data corresponding to the each RGB image in one or more band-subsets having similar spectral signatures, and extracting, by the processing unit, one or more spectral and one or more spatial features from the full range hyperspectral data corresponding to the each RGB image based on the organising.
12 . The method as claimed in claim 11 , the method further comprises determining, by the processing unit, one or more parameters related to at least one of an agriculture and health field based on the one or more extracted spectral features, the one or more extracted spatial features and a third pre-trained dataset.
13 . The method as claimed in claim 11 , wherein the third pre-trained dataset comprises a plurality of data trained based on a hyperspectral data and a RGB-depth data associated with a plurality of events associated with at least one of the agriculture and the health field.
14 . A system for extracting a full range hyperspectral data from one or more RGB images, the system comprising: a transceiver unit, configured to receive from one or more camera devices, one or more RGB images; and a processing unit, configured to: pre-process, the one or more RGB images, estimate, an illumination component associated with each pre-processed RGB image of the one or more pre-processed RGB images based on a first pre-trained dataset, wherein the first pre-trained dataset comprises a plurality of data trained based on a depth value associated with each object captured in each image of a plurality of RGB images, remove, the illumination component from the each pre-processed RGB image, track, a trajectory of one or more pixels over one or more frames associated with the each pre-processed RGB image based on an optical flow model, identify, a position of the one or more pixels in one or more adjacent frames of the one or more frames based on a patch defined around said one or more pixels, and extract, the full range hyperspectral data from the each pre-processed RGB image corresponding to the one or more RGB images based on at least one of the removal of the illumination component, the trajectory of the one or more pixels and the position of the one or more pixels.

Description

TECHNICAL FIELD The present invention generally relates to the field of image processing and more particularly, to systems and methods for extracting a full range hyperspectral data from one or more RGB images to at least have at least one of one or more spectral and quantitative information to improve accuracy of various application in agriculture, health and other allied fields using imaging systems. BACKGROUND OF THE DISCLOSURE The following description of related art is intended to provide background information pertaining to the field of the disclosure. This section may include certain aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section be used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of prior art. With an enhancement in the field of digital technologies, the image processing technologies and imaging systems are also enhanced to a great extent. A camera phone/device, like many complex systems, is a result of converging and enabling technologies. The camera phone is a smart/feature mobile phone/device which is able to capture photographs and often record video using one or more built-in digital cameras and can also send the resulting image/video over the telephone function. The principal advantages of such devices are cost and compactness and use of their touch screens to direct their camera to focus on a particular object in the field of view, giving even an inexperienced user a degree of focus control exceeded only by seasoned photographers using manual focus. Digital cameras when compared with the camera phone/device, a consumer-viable camera in a mobile phone would require far less power and a higher level of camera electronics integration to permit miniaturization. A ‘smart device or smart computing device or user equipment (UE) or user device’ refers to any electrical, electronic, electro-mechanical computing device or equipment or a combination of one or more of the above devices. Also, a ‘smartphone’ or ‘feature mobile phone’ is one type of “smart computing device” that refers to a mobility wireless cellular connectivity device that allows end users to use services on cellular networks such as including but not limited to 2G, 3G, 4G, 5G and/or the like mobile broadband Internet connections with an advanced mobile operating system which combines features of a personal computer operating system with other features useful for mobile or handheld use. Also, today a wireless network, that is widely deployed to provide various communication services such as voice, video, data, advertisement, content, messaging, broadcasts, etc. usually have multiple access networks, support communications for multiple users by sharing the available network resources. One example of such a network is the Evolved Universal Terrestrial Radio Access (E-UTRA) which is a radio access network standard meant to be a replacement of the UMTS and HSDPA/HSUPA technologies specified in 3GPP releases 5 and beyond. Unlike HSPA, LTE's E-UTRA is an entirely new air interface system, unrelated to and incompatible with W-CDMA. It provides higher data rates, lower latency and is optimized for packet data. The earlier UTRAN is the radio access network (RAN) was defined as a part of the Universal Mobile Telecommunications System (UMTS), a third generation (3G) mobile phone technology supported by the 3rd Generation Partnership Project (3GPP). The UMTS, which is the successor to Global System for Mobile Communications (GSM) technologies, currently supports various air interface standards, such as Wideband-Code Division Multiple Access (W-CDMA), Time Division-Code Division Multiple Access (TD-CDMA), and Time Division-Synchronous Code Division Multiple Access (TD-SCDMA). The UMTS also supports enhanced 3G data communications protocols, such as High-Speed Packet Access (HSPA), which provides higher data transfer speeds and capacity to associated UMTS networks. As the demand for mobile data and voice access continues to increase, research and development continue to advance the technologies not only to meet the growing demand for access, but to advance and enhance the user experience with user device. Some of the technologies that have evolved starting GSM/EDGE, UMTS/HSPA, CDMA2000/EV-DO and TD-SCDMA radio interfaces with the 3GPP Release 8, e-UTRA is designed to provide a single evolution path for providing increases in data speeds, and spectral efficiency, and allowing the provision of more functionality. 3GPP has also introduced a new technology NB-IoT in release 13. The ow end IoT applications can be met with this technology. It has taken efforts to address IoT markets with completion of standardization on NB-IoT. The NB-IoT technology has been implemented in licensed bands. The licensed bands of LTE are used for exploiting this technology. This technology makes use of a minimum system ban