In this work, we examine the literature of active object recognition in the past and present. We note that methods in the past used a notion of recognition ambiguity in order to motivate an agent to move the camera in order to take more views and disambiguate the object. Present methods on the other hand are using deep reinforcement learning to learn camera movement policies from the data. We show on a public dataset, that reinforcement learning methods are not superior to a policy of adequately sampling the object view-sphere. Instead of focusing on finding the next best view of the camera, we examine a recent method of quantifying recognition uncertainty in deep learning and its potential application to active object recognition. We find ...
We present new test results for our active object recognition algorithms. The algorithms are used to...
Object recognition is a challenging problem for artificial systems. This is especially true for obje...
Abstract. Statistical machine learning has revolutionized computer vision. Sys-tems trained on large...
An active object recognition system has the advantage of acting in the environment to capture images...
This PhD thesis, conducted in cooperation with ONERA, focuses on active 3D object recognition by an ...
A mobile agent with the task to classify its sensor pattern has to cope with ambiguous information. ...
We propose an active object recognition framework that introduces the recognition self-awareness, wh...
Visual object detection is one of the fundamental tasks in computer vision and robotics. Small scale...
While there have been extensive applications deploying object detection, one of its limitations is t...
Awarded with the Dr. Waldemar Jucker award 2020 of the GSTWhile vision in living beings is an active...
The topic of this thesis is the combination of active learning strategies used in conjunction with ...
Cette thèse, réalisée en coopération avec l’ONERA, concerne la reconnaissance active d’objets 3D par...
The development of reliable and robust visual recognition systems is a main challenge towards the de...
Deep neural networks have reached very high accuracy on object detection but their success hinges on...
We present an active object recognition strategy which combines the use of an attention mechanism fo...
We present new test results for our active object recognition algorithms. The algorithms are used to...
Object recognition is a challenging problem for artificial systems. This is especially true for obje...
Abstract. Statistical machine learning has revolutionized computer vision. Sys-tems trained on large...
An active object recognition system has the advantage of acting in the environment to capture images...
This PhD thesis, conducted in cooperation with ONERA, focuses on active 3D object recognition by an ...
A mobile agent with the task to classify its sensor pattern has to cope with ambiguous information. ...
We propose an active object recognition framework that introduces the recognition self-awareness, wh...
Visual object detection is one of the fundamental tasks in computer vision and robotics. Small scale...
While there have been extensive applications deploying object detection, one of its limitations is t...
Awarded with the Dr. Waldemar Jucker award 2020 of the GSTWhile vision in living beings is an active...
The topic of this thesis is the combination of active learning strategies used in conjunction with ...
Cette thèse, réalisée en coopération avec l’ONERA, concerne la reconnaissance active d’objets 3D par...
The development of reliable and robust visual recognition systems is a main challenge towards the de...
Deep neural networks have reached very high accuracy on object detection but their success hinges on...
We present an active object recognition strategy which combines the use of an attention mechanism fo...
We present new test results for our active object recognition algorithms. The algorithms are used to...
Object recognition is a challenging problem for artificial systems. This is especially true for obje...
Abstract. Statistical machine learning has revolutionized computer vision. Sys-tems trained on large...