Abstract: Accurately detection of logos in media content on media presentation devices is addressed. Logos and products are detected in media content produced in retail deployments using a camera. Logo recognition uses saliency analysis, segmentation techniques, and stroke analysis to segment likely logo regions. Logo recognition may suitably employ feature extraction, signature representation, and logo matching. These three approaches make use of neural network based classification and optical character recognition (OCR). One method for OCR recognizes individual characters then performs string matching. Another OCR method uses segment level character recognition with N-gram matching. Synthetic image generation for training of a neural net classifier and utilizing transfer learning features of neural networks are employed to support fast addition of new logos for recognition.

Abstract: Audio distortion compensation methods to improve accuracy and efficiency of audio content identification are described. The method is also applicable to speech recognition. Methods to detect the interference from speakers and sources, and distortion to audio from environment and devices, are discussed. Additional methods to detect distortion to the content after performing search and correlation are illustrated. The causes of actual distortion at each client are measured and registered and learnt to generate rules for determining likely distortion and interference sources. The learnt rules are applied at the client, and likely distortions that are detected are compensated or heavily distorted sections are ignored at audio level or signature and feature level based on compute resources available. Further methods to subtract the likely distortions in the query at both audio level and after processing at signature and feature level are described.

Abstract: Accurately detection of logos in media content on media presentation devices is addressed. Logos and products are detected in media content produced in retail deployments using a camera. Logo recognition uses saliency analysis, segmentation techniques, and stroke analysis to segment likely logo regions. Logo recognition may suitably employ feature extraction, signature representation, and logo matching. These three approaches make use of neural network based classification and optical character recognition (OCR). One method for OCR recognizes individual characters then performs string matching. Another OCR method uses segment level character recognition with N-gram matching. Synthetic image generation for training of a neural net classifier and utilizing transfer learning features of neural networks are employed to support fast addition of new logos for recognition.

Abstract: A system for matching a user device to an electric transport device including a plurality of electric transport devices comprising a first type and a second type configured differently than the first type; and a service provider deploying and tracking the plurality of electric transport devices, and including a processor. The processor is configured to receive a request to initiate a ride of an electric transport device; information regarding user physical characteristics collected via user input to the user device; determine a match of the user physical characteristics to a corresponding type of electric transport device by comparing the user physical characteristics to physical characteristics assigned to the first type of electric transport device and the second type of electric transport device, and select an individual electric transport device from among a collection of the corresponding type of electric transport device based on the match.

Abstract: A system and method for pairing a rider to a suitable electric transport device based on a variety of input parameters is described. The system involves a service provider that deploys at least two differently configured electric transport devices, and processes inputs from a user/rider such as biometric data, the rider's physical characteristics, rider experience level and preferences to pair the rider to a suitable electric transport device based on the inputs.

Abstract: A mobile device responds in real time to media content presented on a media device, such as a television. The mobile device captures temporal fragments of audio-video content on its microphone, camera, or both and generates corresponding audio-video query fingerprints. The query fingerprints are transmitted to a search server located remotely or used with a search function on the mobile device for content search and identification. Audio features are extracted and audio signal global onset detection is used for input audio frame alignment. Additional audio feature signatures are generated from local audio frame onsets, audio frame frequency domain entropy, and maximum change in the spectral coefficients. Video frames are analyzed to find a television screen in the frames, and a detected active television quadrilateral is used to generate video fingerprints to be combined with audio fingerprints for more reliable content identification.

Abstract: A method for providing guided navigation for personal transport devices is described. In one embodiment, the method includes providing a list of predetermined destinations associated with a geographic area, projecting directions to one or more of the destinations on a ground surface located in front of a personal transport device, and providing an option to a user of the personal transport device to select between at least two different destinations. A direction associated with each destination of the at least two destinations may be projected on the ground surface located in front of the personal transport device. The method also includes receiving an input from the user indicating a selection of one of the at least two different destinations and projecting directions to the selected destination on the ground surface located in front of the personal transport device to guide the user to the selected destination.

Abstract: Audio distortion compensation methods to improve accuracy and efficiency of audio content identification are described. The method is also applicable to speech recognition. Methods to detect the interference from speakers and sources, and distortion to audio from environment and devices, are discussed. Additional methods to detect distortion to the content after performing search and correlation are illustrated. The causes of actual distortion at each client are measured and registered and learnt to generate rules for determining likely distortion and interference sources. The learnt rules are applied at the client, and likely distortions that are detected are compensated or heavily distorted sections are ignored at audio level or signature and feature level based on compute resources available. Further methods to subtract the likely distortions in the query at both audio level and after processing at signature and feature level are described.

Abstract: Audio distortion compensation methods to improve accuracy and efficiency of audio content identification are described. The method is also applicable to speech recognition. Methods to detect the interference from speakers and sources, and distortion to audio from environment and devices, are discussed. Additional methods to detect distortion to the content after performing search and correlation are illustrated. The causes of actual distortion at each client are measured and registered and learnt to generate rules for determining likely distortion and interference sources. The learnt rules are applied at the client, and likely distortions that are detected are compensated or heavily distorted sections are ignored at audio level or signature and feature level based on compute resources available. Further methods to subtract the likely distortions in the query at both audio level and after processing at signature and feature level are described.

Abstract: The overall architecture and details of a scalable video fingerprinting and identification system that is robust with respect to many classes of video distortions is described. In this system, a fingerprint for a piece of multimedia content is composed of a number of compact signatures, along with traversal hash signatures and associated metadata. Numerical descriptors are generated for features found in a multimedia clip, signatures are generated from these descriptors, and a reference signature database is constructed from these signatures. Query signatures are also generated for a query multimedia clip. These query signatures are searched against the reference database using a fast similarity search procedure, to produce a candidate list of matching signatures. This candidate list is further analyzed to find the most likely reference matches. Signature correlation is performed between the likely reference matches and the query clip to improve detection accuracy.

Abstract: A method and system for synchronizing the start of group ride rentals of electric transport devices is described. In one embodiment, a method for initiating a group ride for a plurality of users of electric transport devices includes receiving a request from a first user of an electric transport device to initiate a group ride from a first location to a second location. The method also includes adding one or more additional users to the group ride. Each user is associated with a separate billing account with a service provider for the electric transport devices. The method further includes delaying a start of billing for each user included in the group ride by the service provider until each user has located an electric transport device.

Abstract: A method for providing guided navigation for personal transport devices is described. In one embodiment, the method includes providing a list of predetermined destinations associated with a geographic area, projecting directions to one or more of the destinations on a ground surface located in front of a personal transport device, and providing an option to a user of the personal transport device to select between at least two different destinations. A direction associated with each destination of the at least two destinations may be projected on the ground surface located in front of the personal transport device. The method also includes receiving an input from the user indicating a selection of one of the at least two different destinations and projecting directions to the selected destination on the ground surface located in front of the personal transport device to guide the user to the selected destination.

Abstract: An electric scooter with a lighting system that includes a rear mounted light that projects light upward and toward the front of the scooter to illuminate the back of a rider, and side lights that project light to illuminate the sides of a scooter. The lighting system employs a multi-faceted approach to vary intensity and effects for improved visibility in traffic. The light system can be configured to automatically illuminate or change effects in response to road or environmental conditions, or in response to existing or future roadway infrastructure such as autonomous traffic infrastructure or adaptive traffic control systems. The light system may also be integrated with the braking system for signaling a slow down or stop. The system may be controlled by communication between an onboard processor and a personal computing device such as a smart phone that can be docked on the scooter and provide display of information and a means of input.

Abstract: A method for providing guided navigation for personal transport devices is described. In one embodiment, the method includes providing a list of predetermined destinations associated with a geographic area, projecting directions to one or more of the destinations on a ground surface located in front of a personal transport device, and providing an option to a user of the personal transport device to select between at least two different destinations. A direction associated with each destination of the at least two destinations may be projected on the ground surface located in front of the personal transport device. The method also includes receiving an input from the user indicating a selection of one of the at least two different destinations and projecting directions to the selected destination on the ground surface located in front of the personal transport device to guide the user to the selected destination.

Abstract: A mobile device responds in real time to media content presented on a media device, such as a television. The mobile device captures temporal fragments of audio-video content on its microphone, camera, or both and generates corresponding audio-video query fingerprints. The query fingerprints are transmitted to a search server located remotely or used with a search function on the mobile device for content search and identification. Audio features are extracted and audio signal global onset detection is used for input audio frame alignment. Additional audio feature signatures are generated from local audio frame onsets, audio frame frequency domain entropy, and maximum change in the spectral coefficients. Video frames are analyzed to find a television screen in the frames, and a detected active television quadrilateral is used to generate video fingerprints to be combined with audio fingerprints for more reliable content identification.

Abstract: Accurately detection of logos in media content on media presentation devices is addressed. Logos and products are detected in media content produced in retail deployments using a camera. Logo recognition uses saliency analysis, segmentation techniques, and stroke analysis to segment likely logo regions. Logo recognition may suitably employ feature extraction, signature representation, and logo matching. These three approaches make use of neural network based classification and optical character recognition (OCR). One method for OCR recognizes individual characters then performs string matching. Another OCR method uses segment level character recognition with N-gram matching. Synthetic image generation for training of a neural net classifier and utilizing transfer learning features of neural networks are employed to support fast addition of new logos for recognition.

Abstract: A mobile device responds in real time to media content presented on a media device, such as a television. The mobile device captures temporal fragments of audio-video content on its microphone, camera, or both and generates corresponding audio-video query fingerprints. The query fingerprints are transmitted to a search server located remotely or used with a search function on the mobile device for content search and identification. Audio features are extracted and audio signal global onset detection is used for input audio frame alignment. Additional audio feature signatures are generated from local audio frame onsets, audio frame frequency domain entropy, and maximum change in the spectral coefficients. Video frames are analyzed to find a television screen in the frames, and a detected active television quadrilateral is used to generate video fingerprints to be combined with audio fingerprints for more reliable content identification.

Abstract: Methods, apparatus, systems and articles of manufacture of logo recognition in images and videos are disclosed. An example method to detect a specific brand in images and video streams comprises accepting luminance images at a scale in an x direction Sx and a different scale in a y direction Sy in a neural network, and training the neural network with a set of training images for detected features associated with a specific brand.

Abstract: A system for providing a movement assistance to an electric cycle is provided. The system includes circuitry communicatively coupled to an electronically-actuated driving mechanism and a sensor system of the electric cycle. The circuitry receives sensor information associated with the electric cycle through the sensor system and determines an inclination of the electric cycle with respect to an inclination-reference based on the received sensor information. The circuitry further determines occupancy information associated with a seat of the electric cycle based on the received sensor information. Based on the determined inclination and the determined occupancy information, the circuitry controls the electronically-actuated driving mechanism to drive at least one wheel of the electric cycle.

Abstract: A system and method for pairing a rider to a suitable electric transport device based on a variety of input parameters is described. The system involves a service provider that deploys at least two differently configured electric transport devices, and processes inputs from a user/rider such as biometric data, the rider's physical characteristics, rider experience level and preferences to pair the rider to a suitable electric transport device based on the inputs.