We explore the applicability of spectrograms in Deep learning applications and in guiding creative decisions. To this end, we propose Spectrogrand, a novel spectrogram-driven end-to-end Generative AI pipeline creating...
详细信息
ISBN:
(纸本)9798400710759
We explore the applicability of spectrograms in Deep learning applications and in guiding creative decisions. To this end, we propose Spectrogrand, a novel spectrogram-driven end-to-end Generative AI pipeline creating interesting audiovisuals from text prompts and incorporating lightweight computational creativity metrics. this process involves selecting a music piece to underpin the audiovisual, generating an album cover image for the music, and performing neural style transfer on spectrogram chunks to generate the frames for the audiovisual. To democratise the benefits of this pipeline, we open-source the tool, computational creativity metrics, and associated data (1).
A new hybrid shape fitting algorithm is presented which fits a selected template shape into a noisy point cloud. the method uses prior knowledge of the object shape, which is given by a Statistical Shape Model (SSM). ...
详细信息
High-intensity activities in sports like basketball can result in fatigue without proper recovery. this study introduces a collaborative framework that leverages computervision (CV) and Machine Learning for evaluatin...
详细信息
ISBN:
(纸本)9798400710759
High-intensity activities in sports like basketball can result in fatigue without proper recovery. this study introduces a collaborative framework that leverages computervision (CV) and Machine Learning for evaluating jump landings and predicting athletic readiness by modelling Countermovement Jumps (CMJs) biomechanical aspects. Seventeen female collegiate basketball athletes of Sacred Heart University (SHU), CT, USA, participated in weekly CMJs over a 26-week season. through CV-driven semantic analysis of videos, the framework identifies the crucial initial contact and maximum flexion point during jump landings and extracts kinetic and kinematic features of the lower extremities. Next, an inferential analysis is conducted to understand the relationship between these features and the CMJ-driven reactive strength indexmodified (RSImod) score, which measures fatigue and athletic readiness. An XGBoost regressor, trained on the past week's data, then predicted the RSImod score for the following week, which resulted in an MSE of 0.020 and an R-2 of 0.892. Using SHapley Additive exPlanations (SHAP), the framework offers interpretable feedback, aiding coaches in creating personalised training programs and optimising athletic performance while minimising injury risks.
this paper presents a short historical overview of multiple view vision and, in particular, the estimation of both camera geometry and scene models using only images as input. this problem (the structure and motion pr...
详细信息
CamIO (short for "Camera Input-Output") is a novel camera system designed to make physical objects (such as documents, maps, devices and 3D models) fully accessible to blind and visually impaired persons, by...
详细信息
this paper proposes a novel approach to convert a 3D scan to its CAD counterpart. the objective is to extract intermediate sketch planes that well represent the input scan and are close enough to the original design i...
详细信息
Precision farming has greatly benefited from new technologies over the years. the use of multispectral and hyperspectral sensors coupled to Unmanned Aerial Vehicles (UAV) has enabled farms to monitor crops, improve th...
详细信息
this paper presents Master and Margarita, an interactive audiovisual project for web and performance adapting Mikhail Bulgakov's novel of the same name. It aims to address two main research questions. First: how t...
详细信息
Synthetic hand pose data has been frequently used in vision based hand gesture recognition. However existing synthetic hand pose generators are not able to detect intersection between various hand parts and can synthe...
详细信息
ISBN:
(纸本)9784901122160
Synthetic hand pose data has been frequently used in vision based hand gesture recognition. However existing synthetic hand pose generators are not able to detect intersection between various hand parts and can synthesize self intersecting poses. Using such data may lead to learning wrong models. We propose a method to eliminate self intersecting synthetic hand poses by accurately detecting intersections between various hand parts. We model each hand part as a convex hull and calculate pairwise distance between the parts, labeling any pair with a negative distance as intersecting. A hand pose with at least one pair of intersecting parts is labeled as self intersecting. We show experimentally that our method is very accurate and performs better than existing techniques. We also show that it is fast enough for offline data generation.
Endoscopic disc surgery requires a process of inserting a guide-needle to the target lumbar disc. And the insertion path is manually planned by drawing lines on the patient's skin while monitoring the fluoroscopic...
详细信息
ISBN:
(纸本)9788993215090
Endoscopic disc surgery requires a process of inserting a guide-needle to the target lumbar disc. And the insertion path is manually planned by drawing lines on the patient's skin while monitoring the fluoroscopic view of the lumbar. Such operative procedure inevitably exposes both surgeon and patient to the fluoroscopic radiation emitted from c-arm for a long time. To reduce the radiation exposure time, this study proposes a computer assisted operative planning method implemented by using computervision and computergraphicstheory. this method calculates the 3-dimensional path line of guide-needle from multiple triangular planes. Triangular planes can be obtained by analyzing 2-dimensional images of patient's disc in 3 different angles from rotationally movable c-arm. Additionally, a method of guiding robot's control based on the 3-dimensional needle path was developed by implementing the Hand-eye ( end-effector and camera) calibration. Hand-eye calibration method calculates the geometric transformation matrix between the c-arm coordinate system and base of guidance robot coordinate system. the proposed system was then tested for its accuracy.
暂无评论