Abstract: An auto clean machine, comprising: an optical sensor; a light source, configured to generate a first light pattern; and a processing circuit, configured to determine which light pattern is the first light pattern if the optical sensor senses more than one light pattern.

Abstract: A control apparatus for an auto clean machine comprising a light source configured to emit light to illuminate at least one light region outside and in front of the auto clean machine. The control apparatus comprises: a first image sensing area, configured to sense a first brightness distribution of the light region, wherein a resolution for a first direction of the first image sensing area is higher than a resolution for a second direction of the first image sensing area; and a processor, configured to control movement of the auto clean machine according the first brightness distribution.

Abstract: An optical navigation device comprising: a processing circuit; a first light source, configured to emit first light; a cover; at least one second light source, configured to emit second light toward the cover; and an first optical sensor, configured to sense first optical data generated according to the first light and to sense second optical data generated according to the second light on the cover. The processing circuit determines a dirtiness level of the cover based on the second optical data sensed by the first optical sensor. The optical navigation device can further comprise a second optical sensor. Also, an optical navigation device which can avoid the interference of another optical navigation device is also disclosed.

Abstract: An image capturing device comprising an image sensor. The image sensor comprises: a first sensing region, having a first sensing threshold; and a second sensing region, having a second sensing threshold lower than the first sensing threshold. At least one object image is determined to be invalid when the object image captured by the first sensing region has brightness formation lower the first sensing threshold. At least one the object image is determined to be invalid when the object image captured by the second sensing region has brightness formation lower the second sensing threshold. The present invention also discloses a distance measuring device using the image sensor.

Abstract: An image recognition system includes a processing module, a sensor module, and a database. The sensor module is electrically connected to the processing module. The database is electrically connected to the processing module. The sensor module configured for capturing at least one image. The at least one image is stored in the database. The processing captures a contour of an object from the at least one image and separates the contour of the object into a plurality of portions. A plurality of arrangements is defined between the portions of the contour of the object. The processing module determines a state of the contour of the object based on the arrangements.

Abstract: An object surface managing method comprising: (a) emitting detecting light to the groove via alight source; (b) receiving first reflected detecting light from the surface and second reflected detecting light from a bottom of the groove via a light sensor; and (c) calculating a groove depth of the groove according to the first reflected detecting light and the second reflected detecting light.

Abstract: An optical device, comprising: a processing circuit; a light source, configured to emit light to a surface; and an optical sensor, configured to sense optical data generated based on reflected light or scattering light of the light. The processing circuit computes a dirt level of the surface according to the optical data.

Abstract: An image recognition system includes a processing module, a sensor module, and a database. The sensor module is electrically connected to the processing module. The database is electrically connected to the processing module. The sensor module configured for capturing at least one image. The at least one image is stored in the database. The processing captures a contour of an object from the at least one image and separates the contour of the object into a plurality of portions. A plurality of arrangements is defined between the portions of the contour of the object. The processing module determines a state of the contour of the object based on the arrangements.

Abstract: There is provided a moving robot including a first light source module and a second light source module respectively project a first light section and a second light section, which are vertical light sections, in front of a moving direction, wherein the first light section and the second light section cross with each other at a predetermined distance in front of the moving robot so as to eliminate a detection dead zone between the first light source module and the second light source module in front of the moving robot to avoid collision with an object during operation.

Abstract: An image noise compensating system, comprising: a distance determining device, configured to determine whether a distance is larger than a distance threshold or not; an image sensor, comprising at least one image sensing unit, wherein the image sensor forms a combined image sensing unit when the distance is smaller than the distance threshold and senses images without forming the combined image sensing unit when the distance is larger than the distance threshold, wherein a width of an area that the combined image sensing unit can sense is larger than a width of an area that the image sensing unit can sense; a noise compensating circuit, configured to compensate image noises; and a control circuit, configured to calculate a location of the image noise compensating system.

Abstract: There is provided an image processing device including a light sensor and a processor. The light sensor is used to detect light and output an image frame. The processor identifies intensity of ambient light according to an image parameter associated with the image frame. When the ambient light is identified to be strong enough, the processor performs an object identification directly using the image frame. When the ambient light is identified to be not enough, the processor firstly converts the image frame to a converted image using a machine learning model, and then performs the object identification using the converted image.

Abstract: A detecting device for detecting liquid or colloid, comprising: a light emitting device, configured to emit first light, wherein a first angle between a first emitting direction of the first light and a surface when the detecting device is located on the surface, wherein the first angle is larger than 0° and smaller than 90°; an optical sensor, configured to detect first optical data generated based on the first light; and a processing circuit, configured to determine if the liquid or the colloid exists in a predetermined range of the detecting device based on the first optical data. An automatic cleaner applying the detecting device is also disclosed.

Abstract: There is provided a moving robot including a light projector, an image sensor and a processing unit. The light projector projects a vertical light segment toward a moving direction. The image sensor captures, toward the moving direction, an image frame containing a light segment image associated with the vertical light segment. The processing unit calculates a step distance and a segment feature according to the image frame, outputs a flag signal according to the segment feature to indicate whether the calculated step distance is confident or not, and perform a pixel interpolation in calculating the step distance to improve the identification accuracy.

Abstract: There is provided a cleaning robot including a first light source module and a second light source module respectively project a first light section and a second light section, which are vertical light sections, in front of a moving direction, wherein the first light section and the second light section cross with each other at a predetermined distance in front of the cleaning robot so as to eliminate a detection dead zone between the first light source module and the second light source module in front of the cleaning robot to avoid collision with an object during operation.

Abstract: A method for eliminating misjudgment of a reflective light applied to an autonomous robot is provided. The autonomous robot includes a driving system and an optical sensing system that includes a light source and a light sensor. The light source emits a transverse linear light as detection light and the light sensor senses reflective light signals from an object that reflects the detection light. In the method, a frame image including the reflective light signals is captured by the light sensor, characteristics of the reflective light signals are analyzed, and the characteristics of the reflective light signals can be corrected based on the characteristics of previous reflective light signals stored in a memory of the autonomous robot in order to exclude abnormal information. The object can be confirmed based on the corrected characteristics of reflective light signals. The misjudgment caused by the abnormal information can therefore be eliminated.

Abstract: There is provided a smoke detector including a light source, a reflective surface, a light sensor and a processor. The light sensor receives reflected light when the light source emits light toward the reflective surface, and generates a reference detection signal when there is no smoke. The processor receives the detection signal from the light sensor, and automatically selects a set of predetermined condition thresholds according to a profile of the detection signal to be compared with the detection signal thereby determining whether to generate an alarm according to the comparison result.

Abstract: An optical sensing system and a method for eliminating misjudgment of a reflective light are provided. The optical sensing system includes a first light source, a second light source, a light sensor, and a processor. The processor is configured to: control the first light source to scan a horizontal detection area; control the light sensor to capture a first frame by receiving first reflective lights from the horizontal detection area; obtain a first reflection pattern, and analyze the first reflection pattern to determine whether an object is within the first portion; if so, control the second light source to scan a first vertical detection area; control the light sensor to capture a second frame from the first vertical detection area; process the second frame to obtain a second reflection pattern, and analyze the second reflection pattern to determine whether the object is detected by a misjudgment.

Abstract: An image noise compensating system, comprising: a distance determining device, configured to determine whether a distance between an object and an electronic device comprising the image noise compensating system is larger than a distance threshold or not; an image sensor, comprising at least one image sensing unit, wherein the image sensor combines a plurality of image sensing units to sense images when the distance is smaller than the distance threshold and senses images without combining the image sensing units when the distance is larger than the distance threshold; and an noise compensating circuit, configured to compensate image noises according to the images sensed by the image sensor.

Abstract: An image recognition method and system based on deep learning are provided. The image recognition system includes a first recognizing engine, at least one second recognizing engine and a processing circuit. The second recognizing engine is activated to recognize a testing image when the first recognizing engine is recognizing the testing image. The processing circuit determines whether to interrupt the first recognizing engine recognizing the testing image according to a result outputted by the second recognizing engine after the second recognizing engine completes recognition of the testing image.

Abstract: An electronic device control method, for calling a first electronic device in a building, comprising: (a) receiving a call command from an user by the first electronic device; (b) acquiring map information of the building by the first electronic device corresponding to the call command; and (c) driving the first electronic device to go to a user region in which the user is located according to the map information, wherein the user region is a predetermined region of a user location of the user.