BEIJING, Aug. 18, 2023 /PRNewswire/ — WiMi Hologram Cloud Inc. (NASDAQ: WIMI) (“WiMi” or the “Company”), a leading global Hologram Augmented Reality (“AR”) Technology provider, today announced that it developed a Mask R-CNN-based technique for intelligently extracting CSOs (feature space objects) and its reference points brings a breakthrough in the field of high-resolution image processing and matching. The technique utilizes the latest advances in deep learning and computer vision to provide an efficient and accurate solution for automatic image matching and target localization.
High-resolution image processing and matching have been an important research direction in the field of computer vision, but automatic matching has been facing great challenges due to local deformations in images and differences in lighting conditions. Previous methods are often limited by computational complexity and dependence on local features, making it difficult to achieve accurate results. WiMi’s technique can be used to extract CSOs and their reference points on images. With this method, the CSOs can be acquired automatically and provide accurate localization information for the subsequent image matching process.
WiMi’s R&D team successfully solved this challenge by introducing the Mask R-CNN model, a model extension based on Faster R-CNN commonly used for target detection and instance segmentation. The model is unique in that it can simultaneously predict the bounding box, category, mask and key points of a target, providing comprehensive information for image processing tasks.
In this new technique, WiMi first utilizes a large amount of high-resolution remote sensing image data for training the Mask R-CNN model. Through training, the model is able to learn the features of different target instances in the image and accurately predict their bounding boxes, categories, masks and key points. Based on the trained Mask R-CNN model, the technical team further proposes the concept of CSO and the reference point method. CSO refers to target instances with distinctive features, which can be intelligently filtered out by setting thresholds or rules. Reference points, on the other hand, are extracted from CSOs by a mask predictor and a key point predictor, which are used to locate important feature points of target instances.
The technical implementation logic of it is as follows:
Data preparation: first, a dataset of high-resolution remote sensing images for training and evaluation needs to be prepared. The dataset should contain images with different target types and deformation levels.
Model training: the Mask R-CNN model is trained using the prepared dataset. The goal of training is to enable the model to accurately predict the bounding frame, categories, masks and key points of the targets.
CSO reference point extraction: on the trained Mask R-CNN model, intelligent extraction of CSOs and reference points can be achieved by inputting a high-resolution remote sensing image. Definition of CSO: CSO refers to feature space objects, i.e., target instances with distinctive features. Target instances with distinctive features can be filtered out as CSOs by setting some thresholds or rules. Reference point extraction: the mask predictor and key point predictor of the Mask R-CNN model are utilized to extract the mask and key point for each CSO. The Mask Predictor will generate a binary mask for each CSO, which is used to accurately segment the target instance. The key point predictor will predict the key point coordinates of the target instance for locating the important feature points of the target instance.
Application of CSOs and reference points: the extracted CSOs and reference points can be used for a variety of applications, such as high-resolution remote sensing image matching. Depending on the specific application scenario, image matching or other related tasks can be realized based on the location and features of CSOs.
The breakthrough of this technique is that it not only efficiently extracts CSOs and reference points, but also accurately describes the shape and location of target instances. This makes the automatic matching of high-resolution images more accurate and reliable, providing a reliable foundation for subsequent image processing tasks.
The technique brings many important applications and advantages to the field of high-resolution image processing and matching. It can be widely used in the field of remote sensing image processing, such as urban planning, environmental monitoring and resource management, etc. It can help to automatically extract the features of urban buildings, road networks and natural environments, and provide accurate data support for urban planning and resource management. In addition, this technology can also be applied in the fields of security monitoring, traffic management and military reconnaissance, etc. It can help to automatically extract key targets in the monitoring screen and accurately locate them, so as to improve the efficiency and accuracy of security monitoring. In traffic management, the technology can help identify traffic signs, vehicles and pedestrians, providing reliable data support for traffic flow monitoring and intelligent transportation systems.
This technique has achieved remarkable results in related fields and has been widely noticed and recognized. Currently, the technology has been successfully applied to several practical projects with impressive results. For future development, WiMi will continue to strengthen its technology development and innovation, and continuously improve the performance and effect of Mask R-CNN-based CSO and its reference point and intelligent extraction technology. At the same time, the company will actively expand the application areas of the technology, and work with partners from various industries to promote the development of high-resolution image processing and matching technology, and contribute to the progress and development of society.
About WIMI Hologram Cloud
WIMI Hologram Cloud, Inc. (NASDAQ:WIMI) is a holographic cloud comprehensive technical solution provider that focuses on professional areas including holographic AR automotive HUD software, 3D holographic pulse LiDAR, head-mounted light field holographic equipment, holographic semiconductor, holographic cloud software, holographic car navigation and others. Its services and holographic AR technologies include holographic AR automotive application, 3D holographic pulse LiDAR technology, holographic vision semiconductor technology, holographic software development, holographic AR advertising technology, holographic AR entertainment technology, holographic ARSDK payment, interactive holographic communication and other holographic AR technologies.
Safe Harbor Statements
This press release contains “forward-looking statements” within the Private Securities Litigation Reform Act of 1995. These forward-looking statements can be identified by terminology such as “will,” “expects,” “anticipates,” “future,” “intends,” “plans,” “believes,” “estimates,” and similar statements. Statements that are not historical facts, including statements about the Company’s beliefs and expectations, are forward-looking statements. Among other things, the business outlook and quotations from management in this press release and the Company’s strategic and operational plans contain forward−looking statements. The Company may also make written or oral forward−looking statements in its periodic reports to the US Securities and Exchange Commission (“SEC”) on Forms 20−F and 6−K, in its annual report to shareholders, in press releases, and other written materials, and in oral statements made by its officers, directors or employees to third parties. Forward-looking statements involve inherent risks and uncertainties. Several factors could cause actual results to differ materially from those contained in any forward−looking statement, including but not limited to the following: the Company’s goals and strategies; the Company’s future business development, financial condition, and results of operations; the expected growth of the AR holographic industry; and the Company’s expectations regarding demand for and market acceptance of its products and services.
Further information regarding these and other risks is included in the Company’s annual report on Form 20-F and the current report on Form 6-K and other documents filed with the SEC. All information provided in this press release is as of the date of this press release. The Company does not undertake any obligation to update any forward-looking statement except as required under applicable laws.
