-
公开(公告)号：US10402699B1
公开(公告)日：2019-09-03
申请号：US15380120
申请日：2016-12-15
Applicant: HRL Laboratories, LLC
Inventor： Yang Chen , Deepak Khosla , Fredy Monterroza , Ryan M. Uhlenbrock
Abstract: A method for training an automated classifier of input images includes: receiving, by a processing device, a convolution neural network (CNN) model; receiving, by the processing device, training images and corresponding classes, each of the corresponding classes being associated with several ones of the training images; preparing, by the processing device, the training images, including separating the training images into a training set of the training images and a testing set of the training images; and training, by the processing device, the CNN model utilizing the training set, the testing set, and the corresponding classes to generate the automated classifier.
-
公开(公告)号：US10387774B1
公开(公告)日：2019-08-20
申请号：US14609775
申请日：2015-01-30
Applicant: HRL Laboratories, LLC
Inventor： Yongqiang Cao , Yang Chen , Deepak Khosla
IPC: G06N3/08
Abstract: Described is a system for converting convolutional neural networks to spiking neural networks. A convolutional neural network (CNN) is adapted to fit a set of requirements of a spiking neural network (SNN), resulting in an adapted CNN. The adapted CNN is trained to obtain a set of learned weights, and the set of learned weights is then applied to a converted SNN having an architecture similar to the adapted CNN. The converted SNN is then implemented on neuromorphic hardware, resulting in reduced power consumption.
-
23.发明申请公开(公告)号：US20190251358A1
公开(公告)日：2019-08-15
申请号：US16247157
申请日：2019-01-14
Applicant: HRL Laboratories, LLC
Inventor： Deepak Khosla , Ryan M. Uhlenbrock , Huapeng Su , Yang Chen
CPC classification number: G06K9/00718 , G06K9/00744 , G06K9/00765 , G06K9/00771 , G06K9/3233 , G06K9/4628 , G06K9/6271 , G06K2009/00738 , G06N3/0445 , G06N3/0454 , G06N3/08
Abstract: Described is a system for visual activity recognition. In operation, the system detects a set of objects of interest (OI) in video data and determines an object classification for each object in the set of OI, the set including at least one OI. A corresponding activity track is formed for each object in the set of OI by tracking each object across frames. Using a feature extractor, the system determines a corresponding feature in the video data for each OI, which is then used to determine a corresponding initial activity classification for each OI. One or more OI are then detected in each activity track via foveation, with the initial object detection and foveated object detection thereafter being appended into a new detected-objects list. Finally, a final classification is provided for each activity track using the new detected-objects list and filtering the initial activity classification results using contextual logic.
-
公开(公告)号：US10373335B1
公开(公告)日：2019-08-06
申请号：US15399429
申请日：2017-01-05
Applicant: HRL Laboratories, LLC
Inventor： Yang Chen , Jiejun Xu , Deepak Khosla
Abstract: Described is a system for location recognition for mobile platforms, such as autonomous robotic exploration. In operation, an image in front of the platform is converted into a high-dimensional feature vector. The image reflects a scene proximate the mobile platform. A candidate location identification of the scene is then determined. The candidate location identification is then stored in a history buffer. Upon receiving a cue, the system then determines if the candidate location identification is a known location or a new location.
-
公开(公告)号：US20190005330A1
公开(公告)日：2019-01-03
申请号：US15427597
申请日：2017-02-08
Applicant: HRL Laboratories, LLC
Inventor： Ryan M. Uhlenbrock , Deepak Khosla , Yang Chen , Fredy Monterroza
Abstract: Described is a system and method for accurate image and/or video scene classification. More specifically, described is a system that makes use of a specialized convolutional-neural network (hereafter CNN) based technique for the fusion of bottom-up whole-image features and top-down entity classification. When the two parallel and independent processing paths are fused, the system provides an accurate classification of the scene as depicted in the image or video.
-
Patent Agency Ranking
26.发明申请公开(公告)号：US20180341832A1
公开(公告)日：2018-11-29
申请号：US15934767
申请日：2018-03-23
Applicant: HRL Laboratories, LLC
Inventor： Ryan M. Uhlenbrock , Yang Chen , Deepak Khosla
Abstract: Described is a system for converting a convolutional neural network (CNN) designed and trained for color (RGB) images to one that works on infrared (IR) or grayscale images. The converted CNN comprises a series of convolution layers of neurons arranged in a set kernels having corresponding depth slices. The converted CNN is used for performing object detection. A mechanical component of an autonomous device is controlled based on the object detection.
-
公开(公告)号：US09911197B1
公开(公告)日：2018-03-06
申请号：US14204471
申请日：2014-03-11
Applicant: HRL Laboratories, LLC
Inventor： Kyungnam Kim , Changsoo S. Jeong , Deepak Khosla , Yang Chen , Shinko Y. Cheng , Alexander L. Honda , Lei Zhang
CPC classification number: G06T7/204 , G06T7/0026 , G06T7/215 , G06T7/254 , G06T2207/10016 , G06T2207/10032 , G06T2207/30232
Abstract: Described is a system for detecting moving objects using multi-frame motion history images. An input video sequence of consecutive registered image frames is received. The sequence of consecutive registered image frames comprises forward and backward registered image frames registered to a coordinate system of a reference image frame. Frame differences are computed between each of the consecutive registered image frames and the reference image frame. The frame differences are accumulated based on characteristics of the input video sequence to compute a corresponding motion response value. A selected threshold value is then applied to the motion response value to produce at least one binary image used for detection of moving objects in the input video sequence. Additionally, the invention includes a system for adaptive parameter optimization by input image characterization, wherein parameters that are based on characteristics of the image influence the motion detection process.
-
公开(公告)号：US20170300788A1
公开(公告)日：2017-10-19
申请号：US15269777
申请日：2016-09-19
Applicant: HRL Laboratories, LLC
Inventor： Yongqiang Cao , Qin Jiang , Yang Chen , Deepak Khosla
CPC classification number: G06N3/04 , G06K9/42 , G06K9/44 , G06K9/4652 , G06K9/4671 , G06K9/6267
Abstract: Described is a system for object detection in images or videos using spiking neural networks. An intensity saliency map is generated from an intensity of an input image having color components using a spiking neural network. Additionally, a color saliency map is generated from a plurality of colors in the input image using a spiking neural network. An object detection model is generated by combining the intensity saliency map and multiple color saliency maps. The object detection model is used to detect multiple objects of interest in the input image.
-
29.发明授权Object tracking with integrated motion-based object detection (MogS) and enhanced kalman-type filtering 有权具有集成的基于运动的对象检测（MogS）和增强型卡尔曼型滤波的对象跟踪公开(公告)号：US09552648B1
公开(公告)日：2017-01-24
申请号：US14066600
申请日：2013-10-29
Applicant: HRL Laboratories, LLC
Inventor： Lei Zhang , Deepak Khosla , Yang Chen
IPC: G06T7/20
CPC classification number: G06T7/277 , G06K9/00771 , G06K9/3241 , G06T7/254
Abstract: Described is a system for object tracking with integrated motion-based object detection and enhanced Kalman-type filtering. The system detects a location of a moving object in an image frame using an object detection MogS module, thereby generating an object detection. For each image frame in a sequence of image frames, the system predicts the location of the moving object in the next image frame using a Kalman filter prediction module to generate a predicted object location. The predicted object location is refined using a Kalman filter updating module, and the Kalman filter updating module is controlled by a controller module that monitors a similarity between the predicted object location and the moving object's location in a previous image frame. Finally, a set of detected moving object locations in the sequence of image frames is output.
Abstract translation: 描述了一种用于跟踪集成的基于运动的物体检测和增强型卡尔曼滤波的系统。 该系统使用物体检测MogS模块来检测运动物体在图像帧中的位置，从而产生物体检测。 对于图像帧序列中的每个图像帧，系统使用卡尔曼滤波器预测模块预测运动对象在下一图像帧中的位置，以生成预测对象位置。 使用卡尔曼滤波器更新模块来改进预测对象位置，并且卡尔曼滤波器更新模块由控制器模块来控制，该控制器模块监视预先对象位置与先前图像帧中的移动物体的位置之间的相似度。 最后，输出图像帧序列中的一组检测到的移动物体位置。
-
30.发明授权公开(公告)号：US09008366B1
公开(公告)日：2015-04-14
申请号：US13938196
申请日：2013-07-09
Applicant: HRL Laboratories, LLC
Inventor： Kyungnam Kim , Changsoo S. Jeong , Deepak Khosla , Yang Chen , Shinko Y. Cheng , Alexander L. Honda , Lei Zhang
CPC classification number: G06K9/6202 , G06T7/246 , G06T2207/10016 , G06T2207/10032 , G06T2207/30196 , G06T2207/30232 , G06T2207/30241
Abstract: Described is method for object cueing in motion imagery. Key points and features are extracted from motion imagery, and features between consecutive image frames of the motion imagery are compared to identify similar image frames. A candidate set of matching keypoints is generated by matching keypoints between the similar image frames. A ground plane homography model that fits the candidate set of matching keypoints is determined to generate a set of correct matching keypoints. Each image frame of a set of image frames within a selected time window is registered into a reference frame's coordinate system using the homography transformation. A difference image is obtained between the reference frame and each registered image frame, resulting in multiple difference images. The difference images are then accumulated to calculate a detection image which is used for detection of salient regions. Object cues for surveillance use are produced based on the detected salient regions.
Abstract translation: 描述了运动图像中对象提示的方法。 从运动图像中提取关键点和特征，并比较运动图像的连续图像帧之间的特征，以识别相似的图像帧。 通过匹配相似图像帧之间的关键点来生成候选的匹配关键点集合。 确定适合匹配关键点候选组的地平面单应性模型，以生成一组正确的匹配关键点。 在所选择的时间窗口内的一组图像帧的每个图像帧使用单变图变换登记到参考系的坐标系中。 在参考帧和每个注册的图像帧之间获得差分图像，导致多个差分图像。 然后累积差分图像以计算用于检测突出区域的检测图像。 基于检测到的突出区域产生用于监视使用的对象线索。
-
-
-
-
-
-
-
-
-
Search Results
40
records
(took 0.025 seconds)
