-
公开(公告)号：WO2018089158A1
公开(公告)日：2018-05-17
申请号：PCT/US2017/056195
申请日：2017-10-11
Applicant: QUALCOMM INCORPORATED
Inventor： LI, Zhenyang , TAO, Ran , GAVVES, Efstratios , SNOEK, Cornelis Gerardus Maria , SMEULDERS, Arnold Wilhelmus Maria
CPC classification number: G06F16/7844 , G06F16/3334 , G06F16/338 , G06F16/7834 , G06F16/7837 , G06K9/00744 , G06K9/00771 , G06K9/66 , G06N3/0445 , G06N3/0454 , G06N3/084
Abstract: A method of tracking an object across a sequence of video frames using a natural language query includes receiving the natural language query and identifying an initial target in an initial frame of the sequence of video frames based on the natural language query. The method also includes adjusting the natural language query, for a subsequent frame, based on content of the subsequent frame and/or a likelihood of a semantic property of the initial target appearing in the subsequent frame. The method further includes identifying a text driven target and a visual driven target in the subsequent frame. The method still further includes combining the visual driven target with the text driven target to obtain a final target in the subsequent frame.
Abstract translation: 使用自然语言查询在视频帧序列上追踪对象的方法包括接收自然语言查询并基于自然语言查询识别视频帧序列的初始帧中的初始目标 语言查询。 该方法还包括基于后续帧的内容和/或初始目标的语义属性出现在后续帧中的可能性来调整后续帧的自然语言查询。 该方法还包括在随后的帧中识别文本驱动的目标和视觉驱动的目标。 该方法还包括将视觉驱动目标与文本驱动目标相结合以获得后续帧中的最终目标。
-
公开(公告)号：WO2017078886A1
公开(公告)日：2017-05-11
申请号：PCT/US2016/055735
申请日：2016-10-06
Applicant: QUALCOMM INCORPORATED
Inventor： TAO, Ran , GAVVES, Efstratios , SMEULDERS, Arnold Wilhelmus Maria
CPC classification number: G06K9/00758 , G06K9/3241 , G06K9/4628 , G06K9/6234 , G06K2009/3291 , G06N3/04 , G06T7/2033 , G06T7/248 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084
Abstract: A method of tracking a position of a target object in a video sequence includes identifying the target object in a reference frame. A generic mapping is applied to the target object being tracked. The generic mapping is generated by learning possible appearance variations of a generic object. The method also includes tracking the position of the target object in subsequent frames of the video sequence by determining whether an output of the generic mapping of the target object matches an output of the generic mapping of a candidate object.
Abstract translation: 跟踪视频序列中的目标对象的位置的方法包括识别参考帧中的目标对象。 通用映射应用于正在跟踪的目标对象。 通用映射是通过学习通用对象的可能外观变化而生成的。 该方法还包括通过确定目标对象的通用映射的输出是否匹配候选对象的通用映射的输出来追踪目标对象在视频序列的后续帧中的位置。
-
公开(公告)号：WO2018084948A1
公开(公告)日：2018-05-11
申请号：PCT/US2017/052545
申请日：2017-09-20
Applicant: QUALCOMM INCORPORATED
Inventor： TAO, Ran , GAVVES, Efstratios , SMEULDERS, Arnold Wilhelmus Maria
IPC: G06N3/04
CPC classification number: G06N3/0454 , G06K9/00624 , G06K9/3241 , G06K2009/3291 , G06N3/084 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084
Abstract: In one configuration, a visual object tracking apparatus is provided that receives a position of an object in a first frame of a video, and determines a current position of the object in subsequent frames of the video using a Siamese neural network. To facilitate determining the current position of the object, the apparatus may adjust a spatial resolution of an image, adjust a size of a probe region, and/or adjust a scale of a plurality of sampled images. In one configuration, a visual object tracking using a Siamese neural network is provided. The apparatus feeds outputs from a plurality of subnetworks of the Siamese neural network to a comparison layer. In addition, the apparatus compares, at the comparison layer, inputs from the plurality of subnetworks to generate a comparison result. Further, the apparatus combines comparison results based on weights to obtain a final comparison result.
Abstract translation: 在一种配置中，提供了一种视觉对象跟踪装置，其接收视频的第一帧中的对象的位置，并且使用视频确定视频的后续帧中的对象的当前位置 连体神经网络。 为了便于确定对象的当前位置，设备可以调整图像的空间分辨率，调整探测区域的大小和/或调整多个采样图像的比例。 在一种配置中，提供了使用连体神经网络的视觉对象跟踪。 该设备将来自连体神经网络的多个子网络的输出馈送到比较层。 另外，该设备在比较层处比较来自多个子网络的输入以产生比较结果。 此外，该设备将基于权重的比较结果组合以获得最终比较结果。
-
-
Search Results
3
records
(took 0.017 seconds)
