In the era of big data and Internet +, financial sharing services as a new type of financial management model are being widely accepted and applied. A financial sharing system is designed. The system uses Web services...
详细信息
Vision surveillance is an effective way to detect the water accumulation and corrosion in bridge cable anchorage zone. Duo to the closed dark environment and the high reflectivity of metal surfaces in the zone, the ac...
详细信息
Embedded simultaneous localization and mapping (SLAM) aims at providing real-time performances with restrictive hardware resources of advanced perception functions. Localization methods based on visible cameras includ...
详细信息
ISBN:
(数字)9781665496209
ISBN:
(纸本)9781665496209
Embedded simultaneous localization and mapping (SLAM) aims at providing real-time performances with restrictive hardware resources of advanced perception functions. Localization methods based on visible cameras include imageprocessing functions that require frame memory management. This work reduces the dynamic range of input frame and evaluates the accuracy and robustness of real-time SLAM algorithms with quantified frames. We show that the input data can be reduced up to 62% and 75% while maintaining a similar trajectory error lower than 0.15m compared to full precision input images.
In the modern industrial context, laser processes, such as laser cutting and laser welding, are predominantly monitored and partially controlled in specific areas, such as process abort scenarios or axis actuator move...
详细信息
ISBN:
(纸本)9781510684607;9781510684614
In the modern industrial context, laser processes, such as laser cutting and laser welding, are predominantly monitored and partially controlled in specific areas, such as process abort scenarios or axis actuator movements. Industrial driven interfaces like OPC UA or proprietary bus interface recently allow data acquisition from those control units within certain limits. This data can be augmented with highly accurate scientific data sources. In our proposed setup this is achieved by integrating laser acoustic sensors along with high speed cameras operating in visual and thermal spectrum. The variety of available data sources offers a significant potential for further processing and analysis via artificial intelligence (AI), contributing to deeper process understanding and further development of enhanced control algorithms of laser material machining processes. A post-mortem annotation with quality characteristics such as dross formation, surface roughness, welding depth, porosity, crater formation, etc. deliver all premises to develop and train AI based control models. To link all data sources and annotations a common time management and time normal is required. Its time resolution depends on the fastest cycle time governing a control answer, typically executed in the range of sub milliseconds. A time scale smaller than standard AI algorithms typically deliver complex inference results. Our paper presents an approach to close the time gap by introducing a smart control platform capable of capturing and preprocessing data in real time by utilizing hardware accelerated acquisition algorithms and time management (FPGA-MPSoC). The solution was implemented, transferred to a state of the art welding and cutting setup, and successfully tested. A foundation for an AI controlled laser machining process is set.
This research paper presents a comparative study on various machine learning algorithms for sign language detection. The objective of this study is to find the sign language identification method that is most accurate...
详细信息
Blind watermarking is identified as one of the effective method of data hiding in imageprocessing;however, existing literatures shows an adoption of sophisticated technique considering specific attacks. However, a po...
详细信息
ISBN:
(纸本)9783031214370;9783031214387
Blind watermarking is identified as one of the effective method of data hiding in imageprocessing;however, existing literatures shows an adoption of sophisticated technique considering specific attacks. However, a potential gap is found where there is no report of resiliency of using blind watermarking towards resisting lethal threats. Therefore, this manuscript contributes towards offering a computational assessment model by constructing a lethal blind watermarking attacker model where a discrete orthogonal moments are extracted followed by dithering. The model is assessed on multiple modalities of standard medical image dataset as well as deep learning models. The outcome shows presented model accomplishes more than 45% of performance degradation from accuracy perspective. This outcome will offer clear guidelines of using deep learning models considering different medical image modalities to achieve better watermarking performance.
Knowledge distillation is an important network compression technique, which can generate a small student network by learning the knowledge of the teacher network. However, there are two problems in the previous resear...
详细信息
In this paper, a residual multi-scale generative adversarial network (RMSGAN) is introduced for orthogonal frequency division multiplexing (OFDM) systems, which conducts feature extraction via multi-scale feature fusi...
详细信息
Leaf venation is an important characteristic of plant species that can lead to the identification of a plant. The study of leaf venation is laborious if done by manual inspection. This study proposes a leaf venations...
详细信息
Smart inspections of expressway maintenance are collected on road data through vehicle cameras. The vehicle processing equipment combines edge computing to preprocess the collected image to reduce the pressure of data...
详细信息
暂无评论