TMFNet: Three-Input Multilevel Fusion Network for Detecting Salient Objects in RGB-D Images

The task of object identification is fundamental to the operations of an autonomous vehicle. It can be accomplished by using techniques based on a Multisensor Fusion framework, which allows the integration of data coming from different sensors. In this paper, an approach to the synergic interpretation of data provided by thermal and visual sensors is proposed. Such integration is justified by the necessity for solving the ambiguities that may arise from separate data interpretations. The architecture of a distributed Knowledge-Based system is described. It performs an Intelligent Data Fusion process by integrating, in an opportunistic way, data acquired with a thermal and a video (b/w) camera. Data integration is performed at various architecture levels in order to increase the robustness of the whole recognition process. A priori models allow the system to obtain interesting data from both sensors; to transform such data into intermediate symbolic objects; and, finally, to recognize environmental situations on which to perform further processing. Some results are reported for different environmental conditions (i.e. a road scene by day and by night, with and without the presence of obstacles).

Download Full-text

Interpretation Methods and Ambiguity Management in Multimodal Systems

Multimodal Human Computer Interaction and Pervasive Services ◽

10.4018/978-1-60566-386-9.ch005 ◽

2010 ◽

pp. 87-102 ◽

Cited By ~ 6

Author(s):

Maria Chiara Caschera

Keyword(s):

Correct Recognition ◽

General Level ◽

Natural Interaction ◽

User Input ◽

Multimodal Systems ◽

Interpretation Process ◽

Multilevel Fusion

Naturalness and flexibility of the dialogue between users and multimodal systems can produce more than one interpretation and consequently ambiguities. This chapter deals the problem to correctly recognize user input for enabling a natural interaction. In particular, it analyses approaches that have to cope with issues connected to the interpretation process, dividing them into recognition-based, decision-based, and hybrid multilevel fusion strategies, and providing descriptions of some example of these methods. Moreover, this chapter provides classifications of ambiguities classifying them at a more general level in recognition, segmentation, and target ambiguities, and dividing them in a more detailed way in lexical, syntactical, and pragmatic ambiguities. Considering these classifications, this chapter analyses how interpretation methods support the correct recognition of ambiguities. Finally, this chapter presents methods applied after the interpretation process and that integrate it for solving different class of ambiguities using the dialogue between the user and the system.

Download Full-text

Cervical pneumatocyst

Journal of Neurosurgery Spine ◽

10.3171/2011.5.spine10627 ◽

2011 ◽

Vol 15 (3) ◽

pp. 332-335 ◽

Cited By ~ 7

Author(s):

Jason M. Hoover ◽

Doris E. Wenger ◽

Laurence J. Eckel ◽

William E. Krauss

Keyword(s):

Cervical Spine ◽

Carpal Tunnel Syndrome ◽

Neck Pain ◽

Carpal Tunnel ◽

Chronic Neck Pain ◽

Cervical Radiculopathy ◽

Disc Disease ◽

Left Hand ◽

Tunnel Syndrome ◽

Multilevel Fusion

The authors present the case of a 56-year-old right hand–dominant woman who was referred for chronic neck pain and a second opinion regarding a cervical lesion. The patient's pain was localized to the subaxial spine in the midline. She reported a subjective sense of intermittent left arm weakness manifesting as difficulty manipulating small objects with her hands and fingers. She also reported paresthesias and numbness in the left hand. Physical and neurological examinations demonstrated no abnormal findings except for a positive Tinel sign over the left median nerve at the wrist. Electromyography demonstrated bilateral carpal tunnel syndrome with no cervical radiculopathy. Cervical spine imaging demonstrated multilevel degenerative disc disease and a pneumatocyst of the C-5 vertebral body. The alignment of the cervical spine was normal. A review of the patient's cervical imaging studies obtained in 1995, 2007, 2008, and 2010 demonstrated that the pneumatocyst was not present in 1995 but was present in 2007. The lesion had not changed in appearance since 2007. At an outside institution, multilevel fusion of the cervical spine was recommended to treat the pneumatocyst prior to evaluation at the authors' institution. The authors, however, did not think that the pneumatocyst was the cause of the patient's neck pain, and cervical pneumatocysts typically have a benign course. As such, the authors recommended conservative management and repeated MR imaging in 6 months. Splinting was used to treat the patient's carpal tunnel syndrome.

Download Full-text

Inverse Coefficient of Variation Feature and Multilevel Fusion Technique for Hyperspectral and LiDAR Data Classification

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ◽

10.1109/jstars.2019.2962659 ◽

2020 ◽

Vol 13 ◽

pp. 367-381 ◽

Cited By ~ 3

Author(s):

Farah Jahan ◽

Jun Zhou ◽

Mohammad Awrangjeb ◽

Yongsheng Gao

Keyword(s):

Coefficient Of Variation ◽

Data Classification ◽

Lidar Data ◽

Fusion Technique ◽

Multilevel Fusion ◽

Inverse Coefficient

Download Full-text

A Multilevel Fusion System for Multirobot 3-D Mapping Using Heterogeneous Sensors

IEEE Systems Journal ◽

10.1109/jsyst.2019.2927042 ◽

2020 ◽

Vol 14 (1) ◽

pp. 1341-1352 ◽

Cited By ~ 7

Author(s):

Yufeng Yue ◽

Chule Yang ◽

Yuanzhe Wang ◽

P. G. Chaminda Namal Senarathne ◽

Jun Zhang ◽

...

Keyword(s):

Fusion System ◽

Heterogeneous Sensors ◽

Multilevel Fusion

Download Full-text

Predictive Factors for Discharge Destination Following Posterior Lumbar Spinal Fusion: A Canadian Spine Outcome and Research Network (CSORN) Study

Global Spine Journal ◽

10.1177/2192568218797090 ◽

2018 ◽

Vol 9 (4) ◽

pp. 403-408 ◽

Cited By ~ 2

Author(s):

Mina W. Morcos ◽

Fan Jiang ◽

Greg McIntosh ◽

Henry Ahn ◽

Nicolas Dea ◽

...

Keyword(s):

Logistic Regression ◽

Regression Analysis ◽

Blood Transfusion ◽

Lumbar Fusion ◽

Living Alone ◽

Research Network ◽

Discharge Destination ◽

Disability Score ◽

Fusion Surgery ◽

Multilevel Fusion

Study Design: Ambispective cohort study. Objective: Patients spend on average 3 to 7 days in hospital after lumbar fusion surgery. Patients who are unable to be discharged home may require a prolonged hospital stay while awaiting a bed at a rehabilitation facility, adding cost and imposing a considerable burden on the health care system. Our objective is to identify patient or procedure related predictors of discharge destination for patients undergoing posterior lumbar fusion. Methods: Analysis of data from the Canadian Spine Outcomes and Research Network. Patients who underwent lumbar fusion for degenerative pathology between 2008 and 2015 were identified. Multivariable logistic regression analysis was used to identify independent predictors of the discharge destination. Results: A total of 643 patients were identified from the database, 87.1% of the patients (N = 560) were discharged home while 12.9% (N = 83) required discharge to nonhome facilities. Using multivariate logistic regression analysis, the predictors for discharge to a facility rather than home were identified including: increasing age (odds ratio [OR] 1.045, 95% confidence interval [CI] 1.017 -1.075, P < .002), increasing body mass index (BMI) (OR 1.069, 95% CI 1.021 -1.118, P < .004), increasing disability score (OR 1.025, 95% CI 1.004 -1.046, P < .02), living alone preoperatively (OR 1.916, 95% CI 1.004-3.654, P < .05), increasing operating time (OR 1.005, 95% CI 1.003 -1.008, P < .0001), need for blood transfusion (OR 3.32, 95% CI 1.687-6.528, P < .001), and multilevel fusion surgery (OR 1.142, 95% CI 1.007 -1.297, P < .04). Conclusions: Older age, high BMI, living alone, high disability score, extended surgical time, blood transfusion, and multilevel fusion are significant factors that increase the odds of being discharged to facilities other than home. Level of Evidence: Level 3.

Download Full-text