An electronic device for optically checking an appearance of a product for defects includes a first checking device checking a plane of a product and a second checking device checking side surfaces of the product. The first checking device includes a first camera device, a second camera device, and first white and red light sources. The second checking device includes a third camera device, at least one second white light source, and at least one second red light source. When the first white light source or the first red light source are activated, the first and second camera device capture at least one image of a plane. When the second white light source or the second red light source are activated, the third camera device captures at least one image of a side surface.

A spectroscopic camera according to the present disclosure includes a spectroscopic section configured by a variable wavelength interference filter that selectively transmits light at a predetermined wavelength and changes the light to transmitted light, a receiving section configured to receive sensitivity information indicating a sensitivity curve in a wavelength region of a predetermined color imaged by an RGB camera, a wavelength-table generating section configured to generate, based on the sensitivity information, a wavelength table indicating a relation between the predetermined wavelength and a transmission time, which is a time for transmitting the transmitted light, an imaging section configured to acquire a spectral image formed by the transmitted light transmitted through the spectroscopic section, and a control section configured to control the spectroscopic section and the imaging section based on the wavelength table.

An assembly for detecting defects on a bodywork of a motor vehicle that includes a gantry, of inverted U-shaped cross section, shaped to allow the passage of the motor vehicle in a longitudinal direction, from the rear of the gantry to the front of the gantry. The gantry includes an inner surface extending transversely between two lateral free ends and includes a light source suitable for illuminating, in a substantially uniform manner, the bodywork of the motor vehicle during its passage, the gantry including at least one opaque strip extending transversely over the entire length of the inner surface. The assembly includes a plurality of cameras installed at a distance from the gantry, in at least one longitudinal direction, so as to capture images of the bodywork of the motor vehicle during its passage under the gantry, and a detection member suitable for receiving the images captured by the plurality of cameras and for detecting, according to these images, defects in the bodywork, by analyzing the reflection of the opaque strip on the bodywork and by directly recognizing, in the images, defects on the bodywork.

A multi-arm robot used for tunnel lining inspection and defect diagnosis in an operation period, including a moving platform, where an environment detection device and a defect infection device are disposed on the moving platform, the defect infection device is disposed on the moving platform by using a multi-degree-of-freedom mechanical arm, and an attitude detection module is disposed on each multi-degree-of-freedom mechanical arm; a controller receives environmental data and mechanical arm attitude data sensed by the environment detection device and the attitude detection module, and sends a control instruction to the moving platform and the multi-degree-of-freedom mechanical arm according to the environmental data, to implement movement of the robot; and the controller receives tunnel lining structural data sensed by the defect infection device, and performs defect diagnosis. Overall automatic inspection can be implemented both on the surface and inside of the tunnel lining.

Inspection is efficiently performed without lowering inspection accuracy, by performing an inspection using AI processing. An inspection device has a learning unit that generates a learning model by performing learning for discriminating a type of an inspection object by using as teacher data at least a part of classification results obtained by classifying a plurality of inspected objects of a same type as an inspection object into a plurality of types, or acquires the learning model, a calculation unit that outputs numerical data obtained by quantifying a level of classification accuracy of the type of the inspection object, based on a result calculated by inputting the inspection object to the learning model, and a determination unit that determines, by comparing the numerical data with types of thresholds, whether to automatically discriminate the type of the inspection object or to manually discriminate the type of the inspection object.

In order to meet the objectives described above, the present invention provides a robot for detecting breakdown of NORM (Naturally Occurring Radioactive Materials) in a production system, in order to plan operations to remove scale containing radioactive material, and for decommissioning subsea system operations. The fields of application are the area of flow assurance and reservoir management, using operations to chemically remove scale containing NORM in the production system, and to improve the safety of the decommissioning processes of production systems. The invention allows the position of the scale inside the production system to be safely detected, such as, for example, the beginning of the deposit inside a production line, the extension of the deposit, and the end of the deposit, as well as whether the deposit occurred at different points along the production line.

A frame body may be parallel to and proximate with a surface of a structure and extend substantially horizontally from a first side to a second side. At least one first connecting portion may be attached to a first cable to provide for vertical movement of the frame body, and at least one second connection portion may be attached to a second cable to limit undesired movement of the frame body and/or provide constant tension. At least one buffer portion may be located proximate the first side to move vertically on the surface, and at least one buffer portion may be located proximate the second side to move vertically on the surface. A surface imaging device attached to the frame body may let the system image a structure's substantially vertical surface (e.g., an optical camera may photograph an exterior wall of a building as the frame body is moved).

A method of performing a selected task in a tank at least partially filled with an energetic substance includes, in part, configuring a mobile platform to be inherently safe by positioning spark-generating components in either or both of: (i) an inherently safe enclosure that prevents a spark occurring inside the inherently safe enclosure from passing to an exterior of the inherently safe enclosure, and (ii) a spark-neutralizing body formed of at least one non-flammable substance and positioned inside an enclosure, the spark-neutralizing body blocking direct contact between a spark from the enclosed spark-generating component and an energetic substance from occurring inside the at least one enclosure. The method also includes positioning at least one spark-generating component not inside any inherently safe enclosure that prevents a spark occurring inside the inherently safe enclosure from passing to an exterior of the inherently safe enclosure. The sparks are capable of igniting the energetic substances.

Systems and methods for detecting cracks in a surface by analyzing a video, including an full-HD video, of the surface. The video contains successive frames, wherein individual frames of overlapping consecutive pairs of the successive frames have overlapping areas and a crack that appears in a first individual frame of a consecutive pair of the successive frames also appears in at least a second individual frame of the consecutive pair. A fully convolutional network (FCN) architecture implemented on a processing device is then used to analyze at least some of the individual frames of the video to generate crack score maps for the individual frames, and a parametric data fusion scheme implemented on a processing device is used to fuse crack scores of the crack score maps of the individual frames to identify cracks in the individual frames.

An improved vehicle surface scanning system for assessing the damaged surfaces of a vehicle with resulting estimates of repair costs. A mobile scanning booth is assembled in an open-ended tunnel-like rig having a plurality of reflective panels positioned along opposite sides and across the roof of the booth to serve as deflection screens. A plurality of scanner modules are mounted in fixed positions about opposite ends of the booth and positioned to face the interior of the booth. Wheels provide controlled locomotion/movement of the scanning booth over the vehicle. The scanner modules use a combined hybrid methodology of active stereo 3D reconstruction and deflectometry to acquire data measurements along the surfaces of the vehicle incrementally as the booth is moved. The incremental measurement data acquired during the mobile scanning is processed and furthermore combined to produce accurate reports of the damage surfaces and estimates of associated repair costs.