OBJECT IMAGING AND DETECTION SYSTEMS AND METHODS

Abstract

A method including selecting image data of a mechanical mud separation machines (“MMSM”) to detect objects in an object flow and other operational conditions at the MMSM. The image data may be processed by a Deep Neural Network to identify objects in the object flow, operational parameters of the MMSM, and environmental conditions. Additional image data may be selected for additional processing based on the results of the analysis.

Description

Claims

1. A computer-implemented method comprising: receiving image data from at least one imaging device imaging at least one mechanical mud separation machine (“MMSM”);selecting, from the image data, at least one Region of Interest (“ROI”);analyzing, using a Deep Neural Network (“DNN”), the at least one ROI to identify at least one image aspect in the ROI, wherein the image aspect is at least one of an object in an object flow, signal noise, or another physical object;based on results from the analyzing operation, selecting at least one additional ROIs from the image data; andanalyzing the at least one additional ROIs using the DNN.

2. The computer implemented method of claim 1, wherein the at least one image aspect in the at least one ROI is an object in an object flow and the at least one additional ROIs comprises additional image data of the object in the object flow at a falling zone of a first MMSM of the at least one MMSMs.

3. The computer implemented method of claim 2, wherein the selecting operation comprises: associating the at least one ROI with a first-time frame;identifying the falling zone of the first MMSM;determining a second time frame and location within a field of view of the at least one imaging device at which the object will likely be present at a falling zone of an MMSM;selecting additional image data corresponding to the second time frame and location to form one additional ROI.

4. The computer implemented method of claim 3, wherein identifying a falling zone of the first MMSM comprises using a DNN.

5. The computer implemented method of claim 3, wherein selecting additional image data further comprises: determining a size of the additional ROI to capture the entire object.

6. The computer implemented method of claim 5, wherein the size of the additional ROI is 224 × 224 pixels.

7. The method of claim 3, wherein the second time frame occurs earlier in time than the first time frame.

8-20. (canceled)

21. A system comprising at least one computer processor in electronic communication with at least one computer readable storage device storing instructions that, when executed, performs a method, the method comprising: receiving image data from at least one imaging device imaging at least one mechanical mud separation machine (“MMSM”);selecting, from the image data, at least one Region of Interest (“ROI”);analyzing, using a Deep Neural Network (“DNN”), the at least one ROI to identify at least one image aspect in the ROI, wherein the image aspect is at least one of an object in an object flow, signal noise, or another physical object;based on results from the analyzing operation, selecting at least one additional ROIs from the image data; andanalyzing the at least one additional ROIs using the DNN.

22. The system of claim 21, wherein the at least one image aspect in the at least one ROI is an object in an object flow and the at least one additional ROIs comprises additional image data of the object in the object flow at a falling zone of a first MMSM of the at least one MMSMs.

23. The system of claim 22, wherein the selecting operation comprises: associating the at least one ROI with a first-time frame;identifying the falling zone of the first MMSM;determining a second time frame and location within a field of view of the at least one imaging device at which the object will likely be present at a falling zone of an MMSM;selecting additional image data corresponding to the second time frame and location to form one additional ROI.

24. The system of claim 23, wherein identifying a falling zone of the first MMSM comprises using a DNN.

25. The system of claim 24, wherein selecting additional image data further comprises: determining a size of the additional ROI to capture the entire object.

26. The system of claim 25, wherein the size of the additional ROI is 224 × 224 pixels.

27. The system of claim 23, wherein the second time frame occurs earlier in time than the first time frame.

28. A computer readable storage device storing instructions that, when executed, performs a method, the method comprising: receiving image data from at least one imaging device imaging at least one mechanical mud separation machine (“MMSM”);selecting, from the image data, at least one Region of Interest (“ROI”);analyzing, using a Deep Neural Network (“DNN”), the at least one ROI to identify at least one image aspect in the ROI, wherein the image aspect is at least one of an object in an object flow, signal noise, or another physical object;based on results from the analyzing operation, selecting at least one additional ROIs from the image data; andanalyzing the at least one additional ROIs using the DNN.

29. The computer readable storage device storing of claim 28, wherein the at least one image aspect in the at least one ROI is an object in an object flow and the at least one additional ROIs comprises additional image data of the object in the object flow at a falling zone of a first MMSM of the at least one MMSMs.

30. The computer readable storage device storing of claim 29, wherein the selecting operation comprises: associating the at least one ROI with a first-time frame;identifying the falling zone of the first MMSM;determining a second time frame and location within a field of view of the at least one imaging device at which the object will likely be present at a falling zone of an MMSM;selecting additional image data corresponding to the second time frame and location to form one additional ROI.

31. The computer readable storage device storing of claim 30, wherein identifying a falling zone of the first MMSM comprises using a DNN.

32. The computer readable storage device storing of claim 31, wherein selecting additional image data further comprises: determining a size of the additional ROI to capture the entire object.

33. The computer readable storage device storing of claim 32, wherein the size of the additional ROI is 224 × 224 pixels.