Abstract: The low-sensitivity polarization characteristic model calculation unit 31 of the polarized image processing unit 30-1 calculates the low-sensitivity polarization characteristic model on the basis of the low-sensitivity polarized image in the plurality of polarization directions that is generated by the low-sensitivity imaging unit 21. The non-saturation polarized image extraction unit 32 extracts an image in a polarization direction in which saturation has not occurred from the high-sensitivity polarized image in the plurality of polarization directions that is generated by the high-sensitivity imaging unit 22. The high-sensitivity component acquisition unit 33-1 calculates a high-sensitivity polarization characteristic model having the phase component identical to the low-sensitivity polarization characteristic model from an image in a plurality of polarization directions in which saturation has not occurred in the high-sensitivity polarized image.

Abstract: The polarization imaging unit generates a polarized image including pixels for each of a plurality of polarization components. The demosaicing unit calculates a pixel signal for each polarization component by using the pixel signal of the target pixel of the polarized image and the pixel signal of the pixel for each of the identical polarization components located near the target pixel. In one example, a low frequency component is calculated for each polarization component using the pixel signal of the pixel located near the target pixel for each of the identical polarization components. In addition, component information indicating relationship between the low frequency component of the polarization component of the polarized image and the pixel signal of the target pixel is acquired. Furthermore, the pixel signal for each polarization component in the target pixel is calculated based on the low frequency component and the component information for each polarization component.

Abstract: An image acquisition unit 341-1 acquires a polarization image and a non-polarization image indicating a peripheral area of a moving body, such as the peripheral area of a vehicle. A discrimination information generation unit 342-1 uses the polarization image acquired by the image acquisition unit 341-1 and generates analysis object discrimination information indicating a road surface or the like. An image analysis unit 344-1 uses an image of an image analysis area set on the basis of the analysis object discrimination information generated by the discrimination information generation unit 342-1 with respect to the non-polarization image acquired by the image acquisition unit 341-1, and performs a discrimination of an object, such as an obstacle on the road surface. It is possible to efficiently perform a determination of the presence of the object from the non-polarization image of the peripheral area of the moving body.

Abstract: A damage reduction device according to an embodiment of the present technology includes an input unit, a prediction unit, a recognition unit, and a determination unit. The input unit inputs status data regarding a status in a moving direction of a moving body apparatus. The prediction unit predicts a collision with an object in the moving direction on the basis of the status data. The recognition unit recognizes whether the object includes a person. The determination unit determines, when the collision with the object is predicted and it is recognized that the object includes a person, a steering direction of the moving body apparatus in which a collision with the person is avoidable, on the basis of the status data.

Abstract: An information processing apparatus according to an embodiment of the present technology includes a detection unit, an estimation unit, and a judgment unit. The detection unit detects a target object from an input image. The estimation unit estimates a posture of the detected target object. The judgment unit judges a possibility of the target object slipping on the basis of the estimated posture.

Abstract: A polarized image acquisition unit 20 acquires polarized images in a plurality of polarization directions. A reflection information generation unit 30 generates reflection information indicating reflection components from the polarized images in the plurality of polarization directions acquired by the polarized image acquisition unit 20. A reflection information using unit 40 uses the reflection information generated by the reflection information generation unit 30 to acquire an image of a viewed object appearing in the polarized images. A depth estimation unit estimates a depth value of a reflective surface area and acquires a position of the viewed object on the basis of an image of the viewed object appearing in the reflective surface area and the estimated depth value. Therefore, the viewed object positioned in, for example, an area of a blind spot can be easily checked.

Abstract: An information processing apparatus according to an embodiment of the present technology includes a detection unit, an estimation unit, and a prediction unit. The detection unit detects a target object from an input image. The estimation unit estimates a posture of the detected target object. The prediction unit predicts an action of the target object on a basis of the estimated posture.

Abstract: A control apparatus includes an input unit and a control unit. To the input unit, a pickup image of a camera provided to an own vehicle is input. The control unit detects a mirror provided to a different vehicle that exists in front of the own vehicle from the input pickup image, detects a person from a mirror image of the detected mirror, and recognizes a state of the person from an image of the detected person. Further, the control unit performs an alerting process or a control process for the own vehicle to prevent an accident of the own vehicle or the different vehicle in accordance with the recognized state of the person.

Abstract: There is provided an eyeball observation device, which can stably detect a line of sight, the eyeball observation device including: at least one infrared light source configured to radiate polarized infrared light onto an eyeball of a user; and at least one imaging device configured to capture an image of the eyeball irradiated with the polarized infrared light and to be capable of simultaneously capturing a polarization image with at least three directions.

Abstract: A normal-line information generation block 30 generates normal-line information for a frame subject to detection. A data storage block 50 stores normal-line information and the like of a key frame. A motion amount detection block 40 detects a motion amount of an imaging position of the frame subject to detection relative to an imaging position of the key frame on the basis of the normal-line information of the key frame stored in the data storage block 50 and the normal-line information of the frame subject to detection generated by the normal-line information generation block 30. Even if a positional difference of a same point is small or a luminance difference occurs between a taken image of the key frame and a taken image of a current frame, a motion amount of the imaging position of the frame subject to detection relative to the imaging position of the key frame can be accurately detected on the basis of normal-line information. Therefore, an observation position can be accurately detected.

Abstract: A polarized image acquisition section 20 acquires a plurality of polarized images having different polarization directions. The polarized images show, for example, an input indicator for a user interface as a recognition target object. A normal line calculation section 30 calculates normal lines for individual pixels of the recognition target object in accordance with the polarized images acquired by the polarized image acquisition section 20. The normal lines represent information based on the three-dimensional shape of the recognition target object. A recognition section 40 recognizes the object by using the normal lines calculated by the normal line calculation section 30, determines, for example, the type, position, and posture of the input indicator, and outputs the result of determination as input information on the user interface. The object can be recognized easily and with high accuracy.

Abstract: An imaging unit 20 has a configuration in which an identical polarization pixel block made up of a plurality of pixels with an identical polarization direction is provided for each of a plurality of polarization directions and pixels of respective predetermined colors are provided in the identical polarization pixel block. A correction processing unit 31 performs correction processing such as white balance correction on a polarized image generated by the imaging unit 20. A polarized image processing unit 32 separates or extracts a reflection component using the polarized image after the correction processing. By using a polarized image of the separated or extracted reflection component, for example, it is possible to generate normal line information with high accuracy.

Abstract: A third imaging unit including a pixel not having a polarization characteristic is interposed between a first imaging unit and a second imaging unit including a pixel having a polarization characteristic for each of a plurality of polarization directions. A depth map is generated from a viewpoint of the first imaging unit by matching processing using a first image generated by the first imaging unit and a second image generated by the second imaging unit A normal map is generated on the basis of a polarization state of the first image. Integration processing of the depth map and the normal map is performed and a depth map with a high accuracy is generated. The depth map generated by the map integrating unit is converted into a map from a viewpoint of the third imaging unit, and an image free from deterioration can be generated.

Abstract: A depth map generation unit 22 generates a depth map that generates the depth map from images obtained by picking up a subject at a plurality of viewpoint positions by an image pickup unit 21. On the basis of the depth map generated by the depth map generation unit 22, an alignment unit 23 aligns polarized images obtained by the image pickup unit 21 picking up the subject at the plurality of viewpoint positions through polarizing filters in different polarization directions at the different viewpoint positions. A polarization characteristic acquisition unit 24 acquires a polarization characteristic of the subject from a desired viewpoint position by using the polarized images aligned by the alignment unit 23 to obtain the high-precision polarization characteristic with little degradation in temporal resolution and spatial resolution. It becomes possible to acquire the polarization characteristic of the subject at the desired viewpoint position.

Abstract: A polarization image acquisition unit (11) acquires polarization images of three or more polarization directions. A feature quantity computation unit (15) computes image feature quantities on the basis of the acquired polarization images. For example, the luminance of each polarization image is normalized for each pixel, and the normalized luminance of the polarization image is used as the image feature quantity. The luminance of the polarization image changes according to the surface shape of an object. Thus, the image feature quantities computed on the basis of the polarization images are feature quantities corresponding to the surface shape of the object. Image processing, for example, image recognition, feature point detection, feature point matching, or the like, can be performed on the basis of the surface shape of the object using such image feature quantities.

Abstract: An image processing apparatus includes a superimposition processing unit that performs a blending process for a plurality of continuously captured images, wherein the superimposition processing unit is configured to selectively input luminance signal information of a RAW image or a full color image as a processing target image and perform a superimposition process, and performs a process for sequentially updating data that is stored in a memory for storing two image frames so as to enable superimposition of any desired number of images.

Abstract: An image processing apparatus includes a superimposition processing unit that performs a blending process for a plurality of continuously captured images, wherein the superimposition processing unit is configured to selectively input luminance signal information of a RAW image or a full color image as a processing target image and perform a superimposition process, and performs a process for sequentially updating data that is stored in a memory for storing two image frames so as to enable superimposition of any desired number of images.

Abstract: Disclosed herein is an image processing apparatus including an up-sampling section configured to carry out up-sampling processing in order to generate an up-sampled image, a motion-compensated image generation section configured to generate a motion-compensated image as a result of correction processing to adjust a referenced image having the second resolution to a photographing-object position on the up-sampled image by making use of information on a difference between the up-sampled image and the referenced image, a blending processing section configured to generate a blended image as a result of blending processing to blend the up-sampled image with the referenced image, and an output-image generation section configured to receive and process the blended image as well as the up-sampled image in order to generate an output blended image obtained by blending a super-resolution processing-result image with a noise-reduction processing-result image.

Abstract: An image processing device for super resolution is disclosed. The device comprises an upsampling section, a motion compensated image generating section, a blend processing section and an output image generating section wherein filtering processing necessary for generating a difference information is performed twice or less, so that miniaturization of the device and an improvement in processing efficiency are achieved.

Abstract: Provided is an image processing apparatus for correcting a motion blur or an out-of-focus blur of images continuous in time, including an extraction unit for extracting a frequency component not included in an image of interest using a predetermined filter from a corrected image in which the motion blur or the out-of-focus blur is corrected as an image temporally previous to the image of interest aligned with the image of interest, and a synthesis unit for synthesizing the frequency component extracted by the extraction unit with the image of interest.