A remotely-operable portable trail camera includes a processing unit, an image sensor, a zoom lens, and a zoom level detecting and adjusting circuit. A panhead permits the image sensor to be adjusted azimuthally in a left-right direction and elevationally in an upward-downward direction. A panning control circuit controls a motion of the panhead azimuthally in the left-right direction. A tilting control circuit controls a motion of the panhead elevationally in the upward-downward direction. An object detection circuit detects a motion of a target object. In response to the detection of the motion, the processing unit controls the panning control circuit, the tilting control circuit, and the zoom level detecting and adjusting circuit so as to aim the image sensor towards the target object. The panning control circuit, the tilting control circuit, and the zoom level detecting and adjusting circuit are operatively coupled to a cellular transceiver and can be controlled over a cellphone network using an application on a smartphone or other mobile device.

Cameras provide an easy-to-deploy and information-rich datastream for a wide range of ubiquitous sensing and health monitoring applications. However, their unrestricted operation often captures personally identifiable information (PII), preventing their use in privacy-sensitive settings, such as the home, workplace, and hospitals. This disclosure proposes pairing RGB and thermal imaging to robustly detect and remove PII (e.g., an individual's face, skin color, gender, body shape, etc.,) from images before they are stored or sent off the device. A dual camera prototype includes an onboard embedded GPU capable of performing real-time privacy sanitization tasks at 8FPS at under 5 W power consumption. Results show that in the most fail safe settings the system completely removes all PII. In more permissive settings that maintain full compatibility with downstream computer vision methods, 99% of faces are successfully sanitized, facilitating privacy-preserved exercise tracking, in-home activity inferencing, and fall detection.

Cameras provide an easy-to-deploy and information-rich datastream for a wide range of ubiquitous sensing and health monitoring applications. However, their unrestricted operation often captures personally identifiable information (PII), preventing their use in privacy-sensitive settings, such as the home, workplace, and hospitals. This disclosure proposes pairing RGB and thermal imaging to robustly detect and remove PII (e.g., an individual's face, skin color, gender, body shape, etc.,) from images before they are stored or sent off the device. A dual camera prototype includes an onboard embedded GPU capable of performing real-time privacy sanitization tasks at 8FPS at under 5 W power consumption. Results show that in the most fail safe settings the system completely removes all PII. In more permissive settings that maintain full compatibility with downstream computer vision methods, 99% of faces are successfully sanitized, facilitating privacy-preserved exercise tracking, in-home activity inferencing, and fall detection.

[Object] To extract a target region for a far-infrared image with a high level of accuracy.

[Solution] Provided is an image processing device including: an adjustment unit that adjusts any one of a background image which is a far-infrared image showing a background that does not include an object and a target image which is a far-infrared image showing the object, on the basis of a time change model of an observation pixel value; and an extraction unit that extracts a target region including the object in the target image on the basis of a result of comparison between the background image and the target image after the adjustment is performed.

An electro-optical observation system for hunting includes an electronic image detector and an optical unit assigned to the image detector. The observation system further includes a processor configured to indirectly or directly exchange data with the image detector, to analyze an image stream, which was acquired with the image detector, in view of the presence of an object that is sufficiently different from an image background, and to control a user interface to output a notification to a user in the case of the presence detected on the basis of the analysis of the image stream.

An electro-optical observation system for hunting includes an electronic image detector and an optical unit assigned to the image detector. The observation system further includes a processor configured to indirectly or directly exchange data with the image detector, to analyze an image stream, which was acquired with the image detector, in view of the presence of an object that is sufficiently different from an image background, and to control a user interface to output a notification to a user in the case of the presence detected on the basis of the analysis of the image stream.

An information collection apparatus communicates with an external apparatus, acquires first information relating to a use environment of the apparatus and second information corresponding to a target for the inference processing, executes inference processing by applying the second information and third information set on a basis of the first information to the learned model, and sets the third information on a basis of a range of a first threshold of the first information. When the first information is within a range of a second threshold, the third information is selected on a basis of the range of the first threshold of the first information. When the first information is not within the range of the second threshold, the third information is acquired from the external apparatus via the communication unit so that the first information is within the range of the second threshold.

An information collection apparatus communicates with an external apparatus, acquires first information relating to a use environment of the apparatus and second information corresponding to a target for the inference processing, executes inference processing by applying the second information and third information set on a basis of the first information to the learned model, and sets the third information on a basis of a range of a first threshold of the first information. When the first information is within a range of a second threshold, the third information is selected on a basis of the range of the first threshold of the first information. When the first information is not within the range of the second threshold, the third information is acquired from the external apparatus via the communication unit so that the first information is within the range of the second threshold.

An enclosure having: a base face that is opaque or translucent to human eyes viewing from outside of the enclosure and transparent to infrared radiation; and at least two flat, orthogonal mounting faces configured to be overlaid respectively on at least two surfaces of walls and ceiling of a room. A thermal imaging apparatus configured to image based on infrared radiation and mounted within the enclosure with a predetermined orientation relative to the base face to have a designed imaging direction with respect to the room when the enclosure is mounted in the room to have the at least two orthogonal mounting faces overlaid respectively on the at least two surfaces.

Discussed a welding inspection apparatus including a base unit configured to dispose thereon a battery module, as an object to be inspected, a positive electrode connector and a negative electrode connector connected so as to charge and discharge the battery module, a thermal imaging camera configured to photograph a weld portion of the battery module, and a driving unit configured to move the thermal imaging camera, wherein it is possible to determine whether the weld portion is defective using a nondestructive inspection method.