Prosecution Insights
Last updated: November 20, 2026
Application No. 18/891,112

OBJECT DETECTION IN SATELLITE IMAGERY USING OBJECT-SPECIFIC DATA

Non-Final OA §101§103
Filed
Sep 20, 2024
Examiner
SARMA, ABHISHEK
Art Unit
2621
Tech Center
2600 — Communications
Assignee
International Business Machines Corporation
OA Round
1 (Non-Final)
84%
Grant Probability
Favorable
1-2
OA Rounds
0m
Est. Remaining
84%
With Interview

Examiner Intelligence

Grants 84% — above average
84%
Career Allowance Rate
499 granted / 597 resolved
+21.6% vs TC avg
Minimal +1% lift
Without
With
+0.6%
Interview Lift
resolved cases with interview
Fast prosecutor
2y 1m
Avg Prosecution
23 currently pending
Career history
620
Total Applications
across all art units

Statute-Specific Performance

§101
4.5%
-35.5% vs TC avg
§103
76.4%
+36.4% vs TC avg
§102
8.4%
-31.6% vs TC avg
§112
5.5%
-34.5% vs TC avg
Black line = Tech Center average estimate • Based on career data from 597 resolved cases

Office Action

§101 §103
DETAILED ACTION Notice of Pre-AIA or AIA Status The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . In the response to this Office Action, the Examiner respectfully requests that support be shown for language added to any original claims on amendment and any new claims. That is, indicate support for newly added claim language by specifically pointing to page(s) and line numbers in the specification and/or drawing figure(s). This will assist the Examiner in prosecuting this application. Election/Restrictions Applicant's election without traverse of Species II: Figure 5 in the reply filed on 07/09/2026 is acknowledged. Claim Rejections - 35 USC § 101 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 16-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter because claims 16-20 recite a “computer-readable storage media”. The broadest reasonable interpretation of a claim drawn to a computer-readable storage media typically covers forms of non-transitory tangible media and transitory propagating signals per se in view of the ordinary and customary meaning of “computer-readable storage media”, as variations of the term “computer-readable storage media“ are not necessarily considered to limit a media claim to non-transitory embodiments because many disclosures conflate storage media and signals, particularly when the specification is silent. See MPEP 2111.01. The USPTO recognizes that applicants may have claims directed to “computer-readable storage media”, which the USPTO must reject under 35 U.S.C. § 101 as covering both non-statutory subject matter and statutory subject matter. In an effort to assist the patent community in overcoming a rejection or potential rejection under 35 U.S.C. § 101 in this situation, the USPTO suggests the following approach. A claim drawn to such computer-readable storage media that covers both transitory and non-transitory embodiments may be amended to narrow the claim to cover only statutory embodiments to avoid a rejection under 35 U.S.C. § I01 by rewriting the claim to recite "non-transitory computer-readable storage media " to the claim. Cf. Animals -Patentability, 1 077 0ff. Gaz. Pat. Office 24 (April 21, 1987) (suggesting that applicants add the limitation "non-human" to a claim covering a multi-cellular organism to avoid a rejection under 35 U.S.C. § 101). Such an amendment would typically not raise the issue of new matter, even when the specification is silent because the broadest reasonable interpretation relies on the ordinary and customary meaning that includes signals per se. The limited situations in which such an amendment could raise issues of new matter occur, for example, when the specification does not support a non-transitory embodiment because a signal per se is the only viable embodiment such that the amended claim is impermissibly broadened beyond the supporting disclosure. See, e.g., Gentry Gallery, Inc. v. Berkline Corp., 134 F.3d 1473 (Fed. Cir. 1998). Claim Rejections - 35 USC § 103 The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application Publication 2020/0250428 A1 to Ahmed et al. (hereinafter "Ahmed") in view of Foreign Publication CN118982763A to Meng et al. (hereinafter "Meng"). Regarding Claims 1, 11, and 16, Jeong teaches a computer-implemented method, a computer program product, and a computer system comprising: at least one computing device; a set of one or more computer-readable storage media; and program instructions, collectively stored in the set of one or more computer-readable storage media, for causing the at least one computing device to perform computer operations including (Claims 1, 12; Figs. 1, 7; Pata. 75-80 of Ahmed; computer system 700 includes one or more processing units (generally processor 702)… storage unit 716 includes a machine-readable medium 722 on which is stored instructions 724): receiving, by a computing device of the at least one computing device over one or more networks, imaging data from one or more imaging sources, the imaging data being for a selected spatiotemporal dimension and indicating an object detected by at least one imaging source of the one or more imaging sources (Figs. 1, 5-9; Para. 24-64 of Ahmed; CMG module 112 accepts an observed image from the network system 120 and outputs a cloud map to a user of the client system 110. The CMG module 112 may also accept an observed image from the observation system 140. Imagery data may consist of an image or photograph taken from a remote sensing platform… image may be an image having multi-spectral bands (e.g., six or more bands) obtained by a satellite); obtaining, from at least one data source, object-specific data for a selected type of object and for the selected spatiotemporal dimension (Fig. 3; Para. 40-42 of Ahmed; classifications for segments in the observed image may include “cloud” (e.g., segment 310A)… feature set may include soil and regional information as well as weather information such as daily average cloud coverage, daily average precipitation, daily average normal irradiance, daily average relative humidity and daily average solar radiation); processing, using, at least, the computing device, the imaging data and the object-specific data for the selected spatiotemporal dimension to identify whether the object detected by the at least one imaging source is misclassified as the selected type of object, the processing employing an artificial intelligence model (Figs. 1, 5-9; Para. 24-64 of Ahmed; Other techniques may also be used, examples of which include Random Forest Classifiers, Neural Nets, Support Vector Machines, and so on. Once trained, the resulting prediction model can then be used to predict a specific type of data. The predictions versus the benchmark datasets are validated by taking the test cases and relating them back to the true values of a traditional model in effort to validate that the model is working. Validation involves relating the predictions of the model to the true values that were collected… The CMG module 112 may evaluate the precision and/or accuracy of a trained classification model 116 using an evaluation function. For example, the evaluation function may determine an accuracy and precision for the trained classification model 116); and outputting, by the computing device based on the processing, an indication of whether the object is misclassified (Figs. 1, 5-9; Para. 24-64 of Ahmed; For the supervised learning step, data is fed into the ensemble model 806 of multiple MLP and XGBoost models. Multiple MLP and XGBoost models are trained by a subsampled data set with relatively balanced data distribution, so that each model has seen sufficient data in each class. Each model is trained using the important features selected using the feature selection approach… CMG module 112 trains the classification model 116 using indicators (e.g., previously labelled observed images)… The CMG module 112 may evaluate the precision and/or accuracy of a trained classification model 116 using an evaluation function. For example, the evaluation function may determine an accuracy and precision for the trained classification model 116… evaluation function determines that the precision for a trained classification model is 99.5% when using a set of input observed images (e.g., PlanetScope imagery data). Some other examples of an evaluation function are a confusion matrix or an error matrix. The output of the evaluation function may allow visualization of the performance of a machine learning algorithm… The CMG module 112 evaluates, at step 550, the capabilities of the trained multilayer perceptron using an evaluation function. The evaluation function determines the accuracy and/or precision of the multilayer perceptron in correctly determining a classification for a superpixel. Based on the result of evaluation function, the multilayer perceptron may be further trained). Ahmed does not explicitly disclose employing an artificial intelligence model trained to analyze the imaging data and the object-specific data. However, Meng teaches employing an artificial intelligence model trained to analyze imaging data and object-specific data (Fig. 1; Para. 86-93 of Meng; S2: Utilize the training sample library to train and optimize the deep convolutional neural network. A deep convolutional neural network can be used to extract features from multiple sample data in the training sample library, determine the cloud type of the corresponding cloud target through deep learning analysis, and compare the identified cloud type with the actual cloud type, so that the deep convolutional neural network can be optimized and adjusted according to the comparison result. Optimizing and adjusting the deep convolutional neural network may include adjusting the neural network structure and the parameters of each layer of the network. In some optional embodiments, the feature data extracted from the sample data by the deep convolutional neural network can also be selectively adjusted. S3: Acquire the satellite remote sensing image to be measured, analyze the satellite remote sensing image to be measured using the trained and optimized deep convolutional neural network, and identify and determine the cloud type corresponding to the satellite remote sensing image to be measured. The satellite remote sensing cloud type recognition method obtains initial remote sensing sample images to build a training sample library, uses the training sample library to train and optimize a deep convolutional neural network, and uses the trained and optimized deep convolutional neural network to analyze and recognize the satellite remote sensing images to be tested, so as to accurately and quickly identify the cloud target types in the satellite remote sensing images to be tested). Therefore, at the time when the invention was filed, it would have been obvious to a person of ordinary skill in the art to include employing an artificial intelligence model trained to analyze the imaging data and the object-specific data using the teachings of Meng in order to modify the system and method taught by Ahmed. The motivation to combine these analogous arts would have been to provide efficient and accurate cloud classification and identification (Abstract of Meng). Regarding Claims 2, 12, and 17, the combination of Ahmed and Meng teaches that the object detected by the at least one imaging source is classified as a cloud and the object-specific data includes numerical weather data (Fig. 3; Para. 40-42 of Ahmed; classifications for segments in the observed image may include “cloud” (e.g., segment 310A)… feature set may include soil and regional information as well as weather information such as daily average cloud coverage, daily average precipitation, daily average normal irradiance, daily average relative humidity and daily average solar radiation). Regarding Claim 3, the combination of Ahmed and Meng teaches that the processing uses artificial intelligence rule-based processing to perform spatiotemporal matching of the imaging data and the object-specific data to identify whether the object detected in the selected spatiotemporal dimension is misclassified as the selected type of object (Figs. 5-9; Para. 50-64 of Ahmed; Other techniques may also be used, examples of which include Random Forest Classifiers, Neural Nets, Support Vector Machines, and so on. Once trained, the resulting prediction model can then be used to predict a specific type of data. The predictions versus the benchmark datasets are validated by taking the test cases and relating them back to the true values of a traditional model in effort to validate that the model is working. Validation involves relating the predictions of the model to the true values that were collected… The CMG module 112 may evaluate the precision and/or accuracy of a trained classification model 116 using an evaluation function. For example, the evaluation function may determine an accuracy and precision for the trained classification model 116). Regarding Claim 4, the combination of Ahmed and Meng teaches training the artificial intelligence model using historical imaging data and historical object-specific data for one or more spatiotemporal dimensions (Figs. 5-9; Para. 50-64 of Ahmed; For the supervised learning step, data is fed into the ensemble model 806 of multiple MLP and XGBoost models. Multiple MLP and XGBoost models are trained by a subsampled data set with relatively balanced data distribution, so that each model has seen sufficient data in each class. Each model is trained using the important features selected using the feature selection approach… CMG module 112 trains the classification model 116 using indicators (e.g., previously labelled observed images)… The CMG module 112 may evaluate the precision and/or accuracy of a trained classification model 116 using an evaluation function. For example, the evaluation function may determine an accuracy and precision for the trained classification model 116). Regarding Claim 5, the combination of Ahmed and Meng teaches determining that the artificial intelligence model is producing one or more errors; and retraining the artificial intelligence model using current imaging data and current object-specific data to provide a retrained artificial intelligence model to be used in the processing (Figs. 5-9; Para. 50-64 of Ahmed; For the supervised learning step, data is fed into the ensemble model 806 of multiple MLP and XGBoost models. Multiple MLP and XGBoost models are trained by a subsampled data set with relatively balanced data distribution, so that each model has seen sufficient data in each class. Each model is trained using the important features selected using the feature selection approach… CMG module 112 trains the classification model 116 using indicators (e.g., previously labelled observed images)… The CMG module 112 may evaluate the precision and/or accuracy of a trained classification model 116 using an evaluation function. For example, the evaluation function may determine an accuracy and precision for the trained classification model 116… evaluation function determines that the precision for a trained classification model is 99.5% when using a set of input observed images (e.g., PlanetScope imagery data). Some other examples of an evaluation function are a confusion matrix or an error matrix. The output of the evaluation function may allow visualization of the performance of a machine learning algorithm… The CMG module 112 evaluates, at step 550, the capabilities of the trained multilayer perceptron using an evaluation function. The evaluation function determines the accuracy and/or precision of the multilayer perceptron in correctly determining a classification for a superpixel. Based on the result of evaluation function, the multilayer perceptron may be further trained). Regarding Claims 6, 13, and 18, the combination of Ahmed and Meng teaches that the one or more imaging sources include one or more satellites, and the imaging data includes multi-spectral band data generated from one or more images provided by the one or more satellites (Fig. 1; Para. 24-29 of Ahmed; image may be an image having multi-spectral bands (e.g., six or more bands) obtained by a satellite). Regarding Claims 7, 14, and 19, the combination of Ahmed and Meng teaches that the one or more imaging sources include one or more satellites, and the imaging data includes scene classification band data generated from one or more images provided by the one or more satellites (Fig. 1; Para. 24-29 of Ahmed; image may be an image having multi-spectral bands (e.g., six or more bands) obtained by a satellite). Regarding Claim 8, the combination of Ahmed and Meng teaches comprising generating one or more object characteristics based on combining the imaging data and the object-specific data (Fig. 5; Para. 128-149 of Meng; S504: Extracting reflectivity feature data of the cloud target according to the physical feature description information. Different types of clouds have different spectral characteristics, and their reflectivity shown on satellite remote sensing images is also significantly different. The reflectivity feature data of the cloud target can be extracted based on the physical feature description information. S505: Extracting cloud phase characteristic data of the cloud target according to the physical characteristic description information. The cloud phase characteristics are mainly used to reflect the microphysical properties of clouds, such as the multiple scattering characteristics of typical ice crystals and water droplets, which can effectively distinguish ice clouds from water clouds). Regarding Claim 9, the combination of Ahmed and Meng teaches that the object detected by the at least one imaging source is a cloud and the one or more object characteristics include one or more cloud characteristics (Fig. 5; Para. 128-149 of Meng; S504: Extracting reflectivity feature data of the cloud target according to the physical feature description information. Different types of clouds have different spectral characteristics, and their reflectivity shown on satellite remote sensing images is also significantly different. The reflectivity feature data of the cloud target can be extracted based on the physical feature description information. S505: Extracting cloud phase characteristic data of the cloud target according to the physical characteristic description information. The cloud phase characteristics are mainly used to reflect the microphysical properties of clouds, such as the multiple scattering characteristics of typical ice crystals and water droplets, which can effectively distinguish ice clouds from water clouds). Regarding Claim 10, the combination of Ahmed and Meng teaches that the one or more cloud characteristics include one or more properties of the cloud at a selected location and time (Fig. 5; Para. 128-149 of Meng; S504: Extracting reflectivity feature data of the cloud target according to the physical feature description information. Different types of clouds have different spectral characteristics, and their reflectivity shown on satellite remote sensing images is also significantly different. The reflectivity feature data of the cloud target can be extracted based on the physical feature description information. S505: Extracting cloud phase characteristic data of the cloud target according to the physical characteristic description information. The cloud phase characteristics are mainly used to reflect the microphysical properties of clouds, such as the multiple scattering characteristics of typical ice crystals and water droplets, which can effectively distinguish ice clouds from water clouds). Regarding Claims 15 and 20, the combination of Ahmed and Meng teaches that the computer operations further comprise generating one or more object characteristics based on combining the imaging data and the object-specific data, wherein the object detected by the at least one imaging source is a cloud and the one or more object characteristics include one or more cloud characteristics (Fig. 5; Para. 128-149 of Meng; S504: Extracting reflectivity feature data of the cloud target according to the physical feature description information. Different types of clouds have different spectral characteristics, and their reflectivity shown on satellite remote sensing images is also significantly different. The reflectivity feature data of the cloud target can be extracted based on the physical feature description information. S505: Extracting cloud phase characteristic data of the cloud target according to the physical characteristic description information. The cloud phase characteristics are mainly used to reflect the microphysical properties of clouds, such as the multiple scattering characteristics of typical ice crystals and water droplets, which can effectively distinguish ice clouds from water clouds). Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to ABHISHEK SARMA whose telephone number is (571)272-9887. The examiner can normally be reached on Mon - Fri 8:00-5:00. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Amr Awad can be reached on 571-272-7764. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /ABHISHEK SARMA/ Primary Examiner, Art Unit 2621
Read full office action

Prosecution Timeline

Sep 20, 2024
Application Filed
Sep 28, 2026
Non-Final Rejection mailed — §101, §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12793637
DISPLAY PANEL, ELECTRONIC DEVICE, AND DISPLAY DRIVING METHOD
1y 5m to grant Granted Nov 10, 2026
Patent 12784311
FUSION OF DEEP-LEARNING BASED IMAGE RECONSTRUCTION WITH NOISY IMAGE MEASUREMENTS
2y 4m to grant Granted Nov 03, 2026
Patent 12776259
PIXEL CIRCUIT AND DISPLAY DEVICE HAVING THE SAME
1y 5m to grant Granted Oct 27, 2026
Patent 12770426
TRANSPARENT FINGERPRINT SENSOR
2y 2m to grant Granted Oct 20, 2026
Patent 12758372
Method For Determining Periodontal Pocket Depth
2y 1m to grant Granted Oct 13, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

1-2
Expected OA Rounds
84%
Grant Probability
84%
With Interview (+0.6%)
2y 1m (~0m remaining)
Median Time to Grant
Low
PTA Risk
Based on 597 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month