Learning visual context for object detection ∗

نویسندگان

  • Roland Perko
  • Aleš Leonardis
چکیده

Kontekst ima pomembno vlogo pri splošnem zaznavanju prizorov, saj zagotavlja dodatno informacijo o možnih lokacijah objektov v slikah. Detektorji objektov, ki se uporabljajo v računalnǐskem vidu, tovrstne informacijo običajno ne izkoristijo. V članku bomo zato predstavili koncept, kako se lahko kontekstualne informacije naučimo iz primerov slik prizorov. To informacijo bomo uporabili za izračun kontekstnega polja, ki predstavlja apriorno informacijo za detekcijo objektov glede na možne lokacije. Detekcija objektov, ki temelji na lokalnem videzu, je potem selektivno uporabljena le na nekaterih delih slike. Predlagano metodo smo preizkusili na primerih detekcije pešcev, avtomobilov, in oken, pri čemer smo uporabili zahtevne podatkovne zbirke slik urbanih okolij. Rezultati so pokazali, da kontekstualna informacija dopolnjuje lokalno informacijo na podlagi videza, ter tako zmanǰsa kompleksnost iskanja in poveča robustnost detekcije predmetov. Prednost predlagane metode je tudi v tem, da je učenje kontekstualnih konfiguracij za različne kategorije objektov neodvisno od specifičnih modelov za posamezne naloge.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Visual Tracking using Learning Histogram of Oriented Gradients by SVM on Mobile Robot

The intelligence of a mobile robot is highly dependent on its vision. The main objective of an intelligent mobile robot is in its ability to the online image processing, object detection, and especially visual tracking which is a complex task in stochastic environments. Tracking algorithms suffer from sequence challenges such as illumination variation, occlusion, and background clutter, so an a...

متن کامل

Using P300 to Evaluate the Effect of Object Color Knowledge in Novelty Detection

A B S T R A C T Introduction: In an oddball experiment, the context in which novel stimuli are presented affects characteristics of novelty P3, i.e. as long as there is a difficult task in which the difference between standard and target stimuli is small, recurrent presentation of a highly discrepant stimulus can lead to P300 highly similar to novelty P3. Effect of stimulus properties on P300 h...

متن کامل

Thesis for the degree Doctor of Philosophy

In this thesis we address two related aspects of visual object recognition: the use of motion information, and the use of internal supervision, to help unsupervised learning. These two aspects are inter-related in the current study, since image motion is used for internal supervision, via the detection of spatiotemporal events of active-motion and the use of tracking. Most current work in objec...

متن کامل

The contribution of context information: A case study of object recognition in an intelligent car

In this article, we explore the potential contribution of multimodal context information to object detection in an ”intelligent car”. The used car platform incorporates subsystems for the detection of objects from local visual patterns, as well as for the estimation of global scene properties (sometimes denoted ”scene context” or just ”context”) such as the shape of the road area or the 3D posi...

متن کامل

Comparing the Impact of Audio-Visual Input Enhancement on Collocation Learning in Traditional and Mobile Learning Contexts

: This study investigated the impact of audio-visual input enhancement teaching techniques on improving English as Foreign Language (EFL) learnersˈ collocation learning as well as their accuracy concerning collocation use in narrative writing. In addition, it compared the impact and efficiency of audio-visual input enhancement in two learning contexts, namely traditional and mo...

متن کامل

A Biologically Motivated System for Unconstrained Online Learning of Visual Objects

We present a biologically motivated system for object recognition that is capable of online learning of several objects based on interaction with a human teacher. The training is unconstrained in the sense that arbitrary objects can be freely presented in front of a stereo camera system and labeled by speech input. The architecture unites biological principles such as appearance-based represent...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2007