-
公开(公告)号：US11528435B2
公开(公告)日：2022-12-13
申请号：US17134216
申请日：2020-12-25
Applicant: Industrial Technology Research Institute
Inventor： Peter Chondro , De-Qin Gao
Abstract: The disclosure is directed to an image dehazing method and an image dehazing apparatus using the same method. In an aspect, the disclosure is directed to an image dehazing method, and the method would include not limited to: receiving an input image; dehazing the image by a dehazing module to output a dehazed RGB image; recovering image brightness of the dehazed RGB image by a high dynamic range (HDR) module to output an HDR image; and removing reflection of the HDR image by a ReflectNet inference model, wherein the ReflectNet inference model uses a deep learning architecture.
-
公开(公告)号：US20220210350A1
公开(公告)日：2022-06-30
申请号：US17134216
申请日：2020-12-25
Applicant: Industrial Technology Research Institute
Inventor： Peter Chondro , De-Qin Gao
Abstract: The disclosure is directed to an image dehazing method and an image dehazing apparatus using the same method. In an aspect, the disclosure is directed to an image dehazing method, and the method would include not limited to: receiving an input image; dehazing the image by a dehazing module to output a dehazed RGB image; recovering image brightness of the dehazed RGB image by a high dynamic range (HDR) module to output an HDR image; and removing reflection of the HDR image by a ReflectNet inference model, wherein the ReflectNet inference model uses a deep learning architecture.
-
公开(公告)号：US11507776B2
公开(公告)日：2022-11-22
申请号：US16950919
申请日：2020-11-18
Applicant: Industrial Technology Research Institute
Inventor： De-Qin Gao , Peter Chondro , Mei-En Shao , Shanq-Jang Ruan
Abstract: An image recognition method, including: obtaining an image to be recognized by an image sensor; inputting the image to be recognized to a single convolutional neural network; obtaining a first feature map of a first detection task and a second feature map of a second detection task according to an output result of the single convolutional neural network, wherein the first feature map and the second feature map have a shared feature; using an end-layer network module to generate a first recognition result corresponding to the first detection task from the image to be recognized according to the first feature map, and to generate a second recognition result corresponding to the second detection task from the image to be recognized according to the second feature map; and outputting the first recognition result corresponding to the first detection task and the second recognition result corresponding to the second detection task.
-
公开(公告)号：US10748033B2
公开(公告)日：2020-08-18
申请号：US16215675
申请日：2018-12-11
Applicant: Industrial Technology Research Institute
Inventor： Wei-Hao Lai , Pei-Jung Liang , Peter Chondro , Tse-Min Chen , Shanq-Jang Ruan
IPC: G06K9/62
Abstract: The disclosure is directed to an object detection method using a CNN model and an object detection apparatus thereof. In an aspect, the object detection method includes generating a sensor data; processing the sensor data by using a first object detection algorithm to generate a first object detection result; processing the first object detection result by using a plurality of stages of sparse update mapping algorithm to generate a plurality of stages of updated first object detection result; processing a first stage of the stages of updated first object detection result by using a plurality of stages of spatial pooling algorithm between each of stages of sparse update mapping algorithm; executing a plurality of stages of deep convolution layer algorithm to extract a plurality of feature results; and performing a detection prediction based on a last-stage feature result.
-
5.发明授权公开(公告)号：US10699430B2
公开(公告)日：2020-06-30
申请号：US16154738
申请日：2018-10-09
Applicant: Industrial Technology Research Institute
Inventor： Peter Chondro , Wei-Hao Lai , Pei-Jung Liang
Abstract: In one of the exemplary embodiments, the disclosure is directed to a depth estimation apparatus including a first type of sensor for generating a first sensor data; a second type of sensor for generating a second sensor data; and a processor coupled to the first type of sensor and the second type of sensor and configured at least for: processing the first sensor data by using two stage segmentation algorithms to generate a first segmentation result and a second segmentation result; synchronizing parameters of the first segmentation result and parameters of the second sensor data to generate a synchronized second sensor data; fusing the first segmentation result, the synchronized second sensor data, and the second segmentation result by using two stage depth estimation algorithms to generate a first depth result and a second depth result.
-
Patent Agency Ranking
6.发明申请公开(公告)号：US20190353774A1
公开(公告)日：2019-11-21
申请号：US16009207
申请日：2018-06-15
Applicant: Industrial Technology Research Institute
Inventor： Peter Chondro , Pei-Jung Liang
Abstract: In one of the exemplary embodiments, the disclosure is directed to an object detection system including a first type of sensor for generating a first sensor data; a second type of sensor for generating a second sensor data; and a processor coupled to the first type of sensor and the second type of sensor and configured at least for: processing the first sensor data by using a first plurality of object detection algorithms and processing the second sensor data by using a second plurality of object detection algorithms, wherein each of the first plurality of object detection algorithms and each of the second plurality of object detection algorithms include environmental parameters calculated from a plurality of parameter detection algorithms; and determining for each detected object a bounding box resulted from processing the first sensor data and processing the second sensor data.
-
公开(公告)号：US20240177456A1
公开(公告)日：2024-05-30
申请号：US17993881
申请日：2022-11-24
Applicant: Industrial Technology Research Institute
Inventor： Peter Chondro
IPC: G06V10/774 , G06V10/764 , G06V10/77 , G06V10/82 , G06V20/70
CPC classification number: G06V10/774 , G06V10/764 , G06V10/7715 , G06V10/82 , G06V20/70
Abstract: According to an exemplary embodiment, the disclosure provides an object detection method includes not limited to obtaining a set of a plurality of object annotated images in a source domain and have a first image style; obtaining a minority set of a plurality of object annotated images in a target domain and having a second image style; obtaining a majority set of a plurality of unannotated images which are in the target domain and having the second image style; performing an image style transfer to generate a converted set of object annotated images having the second image style; generating object annotation for the majority set of the plurality of unannotated images in the second image style to change from the majority set of a plurality of unannotated images into a majority set of a plurality of annotated images; and performing an active domain adaptation to generate an object detection model.
-
公开(公告)号：US20220114383A1
公开(公告)日：2022-04-14
申请号：US16950919
申请日：2020-11-18
Applicant: Industrial Technology Research Institute
Inventor： De-Qin Gao , Peter Chondro , Mei-En Shao , Shanq-Jang Ruan
Abstract: An image recognition method, including: obtaining an image to be recognized by an image sensor; inputting the image to be recognized to a single convolutional neural network; obtaining a first feature map of a first detection task and a second feature map of a second detection task according to an output result of the single convolutional neural network, wherein the first feature map and the second feature map have a shared feature; using an end-layer network module to generate a first recognition result corresponding to the first detection task from the image to be recognized according to the first feature map, and to generate a second recognition result corresponding to the second detection task from the image to be recognized according to the second feature map; and outputting the first recognition result corresponding to the first detection task and the second recognition result corresponding to the second detection task.
-
9.发明授权公开(公告)号：US10852420B2
公开(公告)日：2020-12-01
申请号：US16009207
申请日：2018-06-15
Applicant: Industrial Technology Research Institute
Inventor： Peter Chondro , Pei-Jung Liang
IPC: G01S13/86 , G01S13/931 , G01S7/41
Abstract: In one of the exemplary embodiments, the disclosure is directed to an object detection system including a first type of sensor for generating a first sensor data; a second type of sensor for generating a second sensor data; and a processor coupled to the first type of sensor and the second type of sensor and configured at least for: processing the first sensor data by using a first plurality of object detection algorithms and processing the second sensor data by using a second plurality of object detection algorithms, wherein each of the first plurality of object detection algorithms and each of the second plurality of object detection algorithms include environmental parameters calculated from a plurality of parameter detection algorithms; and determining for each detected object a bounding box resulted from processing the first sensor data and processing the second sensor data.
-
10.发明申请公开(公告)号：US20200184260A1
公开(公告)日：2020-06-11
申请号：US16215675
申请日：2018-12-11
Applicant: Industrial Technology Research Institute
Inventor： Wei-Hao Lai , Pei-Jung Liang , Peter Chondro , Tse-Min Chen , Shanq-Jang Ruan
IPC: G06K9/62
Abstract: The disclosure is directed to an object detection method using a CNN model and an object detection apparatus thereof. In an aspect, the object detection method includes generating a sensor data; processing the sensor data by using a first object detection algorithm to generate a first object detection result; processing the first object detection result by using a plurality of stages of sparse update mapping algorithm to generate a plurality of stages of updated first object detection result; processing a first stage of the stages of updated first object detection result by using a plurality of stages of spatial pooling algorithm between each of stages of sparse update mapping algorithm; executing a plurality of stages of deep convolution layer algorithm to extract a plurality of feature results; and performing a detection prediction based on a last-stage feature result.
-
-
-
-
-
-
-
-
-
Search Results
11
records
(took 0.017 seconds)
