Abstract: The disclosure provides an update image map method applied to a vehicle, which comprising the following steps of: receiving a message used to determine whether conditions for updating an image map are met; determining whether the conditions for updating the image map are met according to the message; when it is determined that the conditions for updating the image map are met, receiving a vehicle information and capturing images from one or more cameras; processing the images based on lens characteristics of the one or more cameras and the vehicle information; and writing the processed images to a corresponding location on the image map based on the received vehicle information.

Abstract: This invention provides a method for detecting object, which comprises receiving an image; and executing a deep neural network architecture for the image to obtain one or more object bounding box, wherein the deep neural network architecture comprises a two-dimensional discrete wavelet transform.

Abstract: A method for object and key-point detection, comprising: receiving an image, executing a deep neural network architecture for the image to obtain one or more object bounding boxes; executing the deep neural network architecture for the one or more object bounding boxes to obtain one or more key-point positions corresponding to the one or more object bounding boxes; and outputting the one or more object bounding boxes and the one or more key-point positions.

Abstract: This disclosure provides a method for determining visual and auditory attentiveness of vehicle driver, which comprises: determining a visual attentiveness of a driver according to an image captured by a camera installed inside the vehicle; determining a recognition attentiveness of the driver according to sounds obtained by a microphone installed inside the vehicle; deciding whether to issue a reminder to the driver based on the visual attentiveness and the recognition attentiveness of the driver; when it is necessary to remind the driver after determining the driver's visual and recognition attentiveness, one or a combination of reminder steps will be executed; the reminder steps comprising: issuing a visual reminder by a display device in the vehicle; and issuing a auditory reminder by a speaker in the vehicle.

Abstract: The present invention provides a driving assistance system and a driving assistance computation method that utilize a deep neural network architecture to achieve object detection and semantic segmentation functionalities in a single inference of the same model.

Abstract: A screw supplying module includes a main body, a feeding body and a holding module. The main body includes a second portion, a third portion and a hollow part. The holding module includes a screw chamber, a plurality of clamping pieces, an elastic piece and a fixing piece. The screw chamber includes an input portion, an outer ring wall and an inner space. The plurality of clamping pieces are inserted into the plurality of holes respectively. Accordingly, the plurality of clamping pieces are partially located in the inner space and are partially exposed from the holes of the screw chamber. The elastic piece is sleeved on the outer ring wall, and the elastic piece abuts against the part of the plurality of clamping pieces exposed from the holes. The fixing piece is sleeved on the outer ring wall and is configured to fix the elastic piece.

Abstract: A screw supplying module includes a main body, a feeding body and a holding module. The main body includes a second portion, a third portion and a hollow part. The holding module includes a screw chamber, a plurality of clamping pieces, an elastic piece and a fixing piece. The screw chamber includes an input portion, an outer ring wall and an inner space. The plurality of clamping pieces are inserted into the plurality of holes respectively. Accordingly, the plurality of clamping pieces are partially located in the inner space and are partially exposed from the holes of the screw chamber. The elastic piece is sleeved on the outer ring wall, and the elastic piece abuts against the part of the plurality of clamping pieces exposed from the holes. The fixing piece is sleeved on the outer ring wall and is configured to fix the elastic piece.

Abstract: The disclosure is directed to an object detection method using a CNN model and an object detection apparatus thereof. In an aspect, the object detection method includes generating a sensor data; processing the sensor data by using a first object detection algorithm to generate a first object detection result; processing the first object detection result by using a plurality of stages of sparse update mapping algorithm to generate a plurality of stages of updated first object detection result; processing a first stage of the stages of updated first object detection result by using a plurality of stages of spatial pooling algorithm between each of stages of sparse update mapping algorithm; executing a plurality of stages of deep convolution layer algorithm to extract a plurality of feature results; and performing a detection prediction based on a last-stage feature result.

Abstract: The disclosure is directed to an object detection method using a CNN model and an object detection apparatus thereof. In an aspect, the object detection method includes generating a sensor data; processing the sensor data by using a first object detection algorithm to generate a first object detection result; processing the first object detection result by using a plurality of stages of sparse update mapping algorithm to generate a plurality of stages of updated first object detection result; processing a first stage of the stages of updated first object detection result by using a plurality of stages of spatial pooling algorithm between each of stages of sparse update mapping algorithm; executing a plurality of stages of deep convolution layer algorithm to extract a plurality of feature results; and performing a detection prediction based on a last-stage feature result.

Abstract: A LED lamp bulb includes an envelope having a tubular neck, a LED driver module including a cladding layer-wrapped circuit board press-fitted into the tubular neck of the envelope in a watertight manner, a LED circuit assembly supported on the circuit board-wrapped circuit board and suspending in the envelope and positive and negative lead wires respectively connected to the cladding layer-wrapped circuit board and disposed outside the envelope, and a lamp head bonded to the outer peripheral wall of the tubular neck of the envelope with the center contact thereof electrically connected with the positive lead wire of the LED driver module and the ring contact thereof electrically connected with the negative lead wire of the LED driver module.

Abstract: A LED lamp bulb includes an envelope having a tubular neck, a LED driver module mounted in the tubular neck of the envelope with a LED circuit assembly thereof suspending in the envelope and positive and negative lead wires thereof respectively extended to the outside of the envelope, a lamp head bonded to the outer peripheral wall of the tubular neck of the envelope with the center contact thereof electrically connected with the positive lead wire of the LED driver module and the ring contact thereof electrically connected with the negative lead wire of the LED driver module, and an adhesive bonding layer sealed in between the LED driver module and the inner peripheral wall of the tubular neck of the envelope in an airtight manner.

Abstract: A LED lamp bulb includes a lamp base, a bulb mounted at the top side of the lamp base, and a circuit board electrically connected to the lamp base and surrounded by the bulb. The circuit board is a one-piece circuit board vertically inserted into the lamp base and thus electrically connected with the lamp base, having one or a number of LEDs mounted at each of opposing first and second sides thereof near the top. The horizontal centerline of each LED at each of the first and second sides of the circuit board defines with the horizontal direction of the first or second side of the circuit board a contained angle within 25°˜45°. Further, the topmost edge of the circuit board is disposed above the elevation of the topmost edge of the lamp base.

Abstract: A LED lamp bulb includes a lamp base, a bulb mounted at the top side of the lamp base, and a circuit board electrically connected to the lamp base and surrounded by the bulb. The circuit board is an one-piece circuit board longitudinally inserted into the inside of the lamp base and thus electrically connected with the lamp base, having one or a number of first light-emitting diodes and one or a number of second light-emitting diodes respectively mounted at respective top ends of opposing first and second sides thereof for enabling the LED lamp bulb to emit light uniformly in all directions. Thus, this one-piece circuit board-based LED lamp bulb greatly saves the installation labor and time. Further, because no any further soldering process is necessary, the invention greatly increases the yield and improves the product quality.

Abstract: A LED candle lamp by controlling the coil to generate a magnetic attractive force to attract the magnet set, the translucent flame-shaped blade is vibrated when the emitted light of the LED lamp is guided by the light guide tube toward the blame-shaped blade body of the translucent flame-shaped blade, causing flame lighting effects. Subject to the arrangement that two magnets of a magnet set are bonded together by an adhesive with the same magnet poles thereof abutted against each other, magnetic field lines can be compressed into a dish, enhancing the effects of magnetic attraction and oscillation of a translucent flame-shaped blade.

Abstract: A window candle includes a holder base defining therein a stepped vertical insertion hole formed of a larger upper first insertion hole and a smaller lower second insertion hole and defining a first annular locating groove between the larger upper first insertion hole and the smaller lower second insertion hole and a second annular locating groove located at the bottom side of the smaller lower section insertion hole, a candle shaft inserted into the stepped vertical insertion hole and selectively positioned in the first annular locating groove or the second annular locating groove, an annular locating member optionally mountable in the first annular locating groove to support the candle shaft in the first annular locating groove, and a lampshell fastened to the top end of the candle shaft by a screw joint and holding therein a light-emitting circuit board.

Abstract: A window candle includes a holder base defining therein a stepped vertical insertion hole formed of a larger upper first insertion hole and a smaller lower second insertion hole and defining a first annular locating groove between the larger upper first insertion hole and the smaller lower second insertion hole and a second annular locating groove located at the bottom side of the smaller lower section insertion hole, a candle shaft inserted into the stepped vertical insertion hole and selectively positioned in the first annular locating groove or the second annular locating groove, an annular locating member optionally mountable in the first annular locating groove to support the candle shaft in the first annular locating groove, and a lampshell fastened to the top end of the candle shaft by a screw joint and holding therein a light-emitting circuit board.

Abstract: A LED candle lamp by controlling the coil to generate a magnetic attractive force to attract the magnet set, the translucent flame-shaped blade is vibrated when the emitted light of the LED lamp is guided by the light guide tube toward the blame-shaped blade body of the translucent flame-shaped blade, causing flame lighting effects. Subject to the arrangement that two magnets of a magnet set are bonded together by an adhesive with the same magnet poles thereof abutted against each other, magnetic field lines can be compressed into a dish, enhancing the effects of magnetic attraction and oscillation of a translucent flame-shaped blade.

Abstract: A method for detecting dead pixels obtains a downsampling set formed by a plurality of sample pixels by downsampling a to-be-tested image, and computes a moving average for each sample pixel to determine whether the sample pixel is a dead pixel candidate. If so, all pixels in a neighborhood of the dead pixel candidate are determined as to-be-detected pixels. For each to-be-detected pixel, a compensated value and a weighted average under a mask are estimated. A hypothetic dead pixel value is obtained by comparing an original pixel value of each to-be-detected pixel and the moving average of the dead pixel candidate. Whether the to-be-detected pixel is a dead pixel is determined by using the original pixel value, the compensated value, the weighted average and the hypothetic dead pixel value.

Abstract: A dynamic decoding lookup table generation method is provided. The generation method includes: receiving a variable length coding (VLC) table; and dynamically establishing an adaptive decoding lookup table from the VLC table according to a target decoding rate and a free system memory resource.

Abstract: A method for detecting dead pixels obtains a downsampling set formed by a plurality of sample pixels by downsampling a to-be-tested image, and computes a moving average for each sample pixel to determine whether the sample pixel is a dead pixel candidate. If so, all pixels in a neighborhood of the dead pixel candidate are determined as to-be-detected pixels. For each to-be-detected pixel, a compensated value and a weighted average under a mask are estimated. A hypothetic dead pixel value is obtained by comparing an original pixel value of each to-be-detected pixel and the moving average of the dead pixel candidate. Whether the to-be-detected pixel is a dead pixel is determined by using the original pixel value, the compensated value, the weighted average and the hypothetic dead pixel value.