TWM290286U - Storage and applied devices based on images obtained from object tracking and recognition technology - Google Patents
Storage and applied devices based on images obtained from object tracking and recognition technology Download PDFInfo
- Publication number
- TWM290286U TWM290286U TW93218725U TW93218725U TWM290286U TW M290286 U TWM290286 U TW M290286U TW 93218725 U TW93218725 U TW 93218725U TW 93218725 U TW93218725 U TW 93218725U TW M290286 U TWM290286 U TW M290286U
- Authority
- TW
- Taiwan
- Prior art keywords
- image
- tracking
- function
- storage
- software
- Prior art date
Links
- 238000003860 storage Methods 0.000 title claims description 53
- 230000005540 biological transmission Effects 0.000 claims description 56
- 238000010191 image analysis Methods 0.000 claims description 16
- 238000000034 method Methods 0.000 claims description 13
- 238000005070 sampling Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 230000033001 locomotion Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 2
- 230000001815 facial effect Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 claims 40
- 238000009434 installation Methods 0.000 claims 6
- 238000012795 verification Methods 0.000 claims 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims 2
- 235000010627 Phaseolus vulgaris Nutrition 0.000 claims 2
- 244000046052 Phaseolus vulgaris Species 0.000 claims 2
- 238000004891 communication Methods 0.000 claims 2
- 238000012790 confirmation Methods 0.000 claims 2
- 241000251468 Actinopterygii Species 0.000 claims 1
- 206010011469 Crying Diseases 0.000 claims 1
- 241000283014 Dama Species 0.000 claims 1
- 206010011878 Deafness Diseases 0.000 claims 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 claims 1
- 241000237536 Mytilus edulis Species 0.000 claims 1
- 231100000895 deafness Toxicity 0.000 claims 1
- JNSGIVNNHKGGRU-JYRVWZFOSA-N diethoxyphosphinothioyl (2z)-2-(2-amino-1,3-thiazol-4-yl)-2-methoxyiminoacetate Chemical compound CCOP(=S)(OCC)OC(=O)C(=N/OC)\C1=CSC(N)=N1 JNSGIVNNHKGGRU-JYRVWZFOSA-N 0.000 claims 1
- 238000006073 displacement reaction Methods 0.000 claims 1
- 208000016354 hearing loss disease Diseases 0.000 claims 1
- 229910052742 iron Inorganic materials 0.000 claims 1
- 210000003205 muscle Anatomy 0.000 claims 1
- 235000020638 mussel Nutrition 0.000 claims 1
- 238000004091 panning Methods 0.000 claims 1
- 238000002360 preparation method Methods 0.000 claims 1
- 238000013519 translation Methods 0.000 claims 1
- 230000004382 visual function Effects 0.000 claims 1
- 238000011179 visual inspection Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 5
- 235000013399 edible fruits Nutrition 0.000 description 5
- 238000012360 testing method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 102000001839 Neurturin Human genes 0.000 description 1
- 108010015406 Neurturin Proteins 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000010587 phase diagram Methods 0.000 description 1
- 235000015170 shellfish Nutrition 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 230000005428 wave function Effects 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Landscapes
- Studio Devices (AREA)
Description
M290286 八 新型說明 【新型所屬之技術領域】 處理ί Ϊ 2 ff f於一種具有靜態圖像及動態影像 # = 2自動追縱及辨識之整合型設備系統,尤指 社i 尸不同程式執行之硬體平台與軟體系統 ΐ g的=1τ丨田景1/象儲存、影像辨識及相關整合性 ί ^ ^彳用特殊演算法模式(如波型演算法) 將貝枓庫搜尋時間大大降低。 ^ 【先前技術】 史綠雙^來由於美國九—事件發生後,市場上對於 斤if犯Λ?後偵防追縱及犯罪事前預防的 越多,相對的影像分析 '影像偵測、影像追 術大ΐ 女越i,大。傳統的影像分析技 =ί 2、、先、臉4辨系統、手寫辨識系統等),門孥管 控糸^,銀行管控系統,警報系統等。 ,、 (DSP)資源中同央時貝^合處耗理立處理器 傳人盾士 AA A L +幻、、、口呆立不此十分正確的 “,因此可以應用的相關裝置也就 例,dcdsij方此利用人臉為 置。受限於傳絲旦/德’又把刀^式、、、°5的影像處理裝 t ® # ^ # M m f 暾 a -欠丨η 士, 文的叶候則正確性舍体诘沾ίγM290286 Eight new descriptions [New technical field] Processing ί 2 ff f is an integrated device system with static image and motion picture # = 2 automatic tracking and identification, especially the hard execution of different programs. Body platform and software system ΐ g = 1τ丨田景 1 / image storage, image recognition and related integration ί ^ ^ 彳 using special algorithm mode (such as waveform algorithm) to greatly reduce the search time of the shellfish library. ^ [Prior Art] Shilu Shuang^ came due to the US Nine-Events, the market is guilty of guilty? After the detection and prevention of crimes and crimes before the prevention, the relative image analysis 'image detection, image chase ΐ大ΐ Female is i, big. Traditional image analysis techniques = ί 2, first, face 4 identification system, handwriting recognition system, etc.), threshold control, bank control system, alarm system, etc. , (DSP) resources in the same time, the time is the same as the processor, the processor AA AL + illusion, and solitude are not very correct, so the related devices that can be applied are also examples, dcdsij In this case, the use of the human face is limited. It is limited to the transmission of the silk, Dan, and the image processing of the knife, type, and °5 t ® # ^ # M mf 暾a - 丨 丨 士, 文叶候The correctness of the body
Hii庫Λ的樣本數增加的時候,搜iGS: 間會因為“斗庫的樣本很多,而呈現類以 M290286 ΐΐί故2卺大大降低了使用者使用的意願,也因此 知格始終居高不下。 赴,本新型發明之目的’即在於解決上述的缺 f柊並㈢加影像分析的正確性及應用性,同時降低其 【新型内容] 傻刹Σ Ϊ目ί之影像分析系統皆有其缺點,不論在影 ί 2 - ΐ ΐ ΐ性Λ t i擴山充性都不足,因而未能有效 分v严合出一低成本並同時兼具精確 刀析之衫像處理分析設備。 置,ί 2作裝置係一種具有影像分析追蹤辨識的裝 (1) 影像辨識追蹤功能的軟體系統及其軟體執 平台; (2) 影像儲存裝置; (3 L可移動式之追蹤攝影機、馬達系統裝置及置 物平台; (4 )數位/類比影像擷取傳送及接收裝置; (5)資訊傳送及接收裝置; 、’ 詈ίί置:ΐ透f數位/類比影像擷取傳送及接收裝 二一物體做多維影像取樣及影像訓練,並透過可 / ^之追蹤攝影機馬達系統裝置來追縱及由軟體 2辨識已經訓練過之物體,當追縱辨識完成= 將已絰追蹤辨識出來之物體影像儲存下來 Π f:相關資料由資訊傳送及接收裝置i送: 位置本並創Λ中Λ用位巧vy寅算法找出特定影像的 圖其Λ “=置下的座標值擷取正確的影像資料 M290286 下,收後 接乂 \)y I — 、' xf\ ,r'l 、 I i /Θ -J - - 1i7 m同影1 e圖右結區像值像中ue下F然4)取}4)D斤化的驟(2及輸 第不將(20alu成和一的影素影nal右果l(B機(C3CB的ο ί數牛"®(送像π 考成們Va分塊出}的像將04V及結発F影FF義D過函程如傳影I 參分我片el區區得03塊的,(2ele)一ooh攝;;h定體經過流}取; 區,圖IX像左,(2區塊後片1X1U出50B3從C2B3們物,透其(1擷入12 像說將(P影中減片右區最圖(pva得約FCCFCFC我是現案 像輸(2 ; «] >'> tj bm j 4 /τ Jt Βί -圖樣像中相片區果塊的(ρ區 h區a後當像F比物的轉如1 if 「_r,T y、—yIF ίΐΛ .r· .1 * fl) J x#l\ I \Jr ___ 式區 利案C「舄塊 們圖片和一區的 ^析圖塊出的像 ,分成 丨 的分 圖舉,象,片 析。式後圖 分算樣彳 彡之將, 塊,計塊影卜時x€影 區權區的1)同pi將2(、e 一頊的P]物,式 像力的塊(8,^(再"^^出區 塊1(的 後.方值 影並。區-式2 y U的塊ϋ』系』們會气疋 下結鬼像之㈣d像要試值則值實上二 時piue(2右U的將的準Μ測異,素、論第m下 同C11片和像門述基d與差值象間理考方乐用 — :.、、/多4上試便並出準Μ空在參^置利 用測,4)得基M,“l,:輸裝 區得}景2,值V圖塊影 02的U式素el成區、q的泰 減(2塊F樣像IX分力 L * )* 塊4)利作後(C較體⑴頻換 影率 即 相結樣影像xe體 ) 塊的的pi物 當得(B當受波波的 定用與同 方{ k認利間相 述 上 用 分區減Ca3同像(P1UBFC他(CFC 區左並F(,的值Va樣h其F、 像中加果式象素1圖11有出1) \—/ : i > 影來時值將02相圖和中,將值el,像h像 將例同素再(2e)成塊去}時素lxe)取32)影 於就呈圖 低C式的 }像形間。 (Δ影的空案 F測形型圖When the number of samples in the Hii library increases, the search for iGS: Because there are a lot of samples in the bucket library, the presentation class is M290286 ΐΐ, so the user's willingness to use is greatly reduced, so the knowledge is always high. Going, the purpose of the new invention is to solve the above-mentioned defects and (3) the correctness and applicability of image analysis, and at the same time reduce its [new content] silly brakes. The image analysis system has its shortcomings. No matter in the shadow ί 2 - ΐ ΐ ΐ Λ ti ti expansion is not enough, so it is not possible to effectively separate a low-cost and at the same time with a precise knife analysis processing equipment. The device is a software system with image analysis and tracking identification (1) image recognition and tracking function and its software platform; (2) image storage device; (3 L movable tracking camera, motor system device and storage platform; (4) Digital/analog image capture transmission and reception devices; (5) Information transmission and reception devices; , ' 詈 ί ί 置 ΐ ΐ f f f f f f f f f f f f f f f f f f f f f f Shadow Training, and through the tracking camera motor system device to track and identify the object that has been trained by the software 2, when the tracking identification is completed = the image of the object that has been tracked and identified is stored Π f: Related information Information transmission and receiving device i send: Location and create a 寅 Λ Λ 寅 寅 寅 algorithm to find a specific image of the map Λ " = set the coordinate value to take the correct image data under M290286, after receiving 乂 \ ) y I — , ' xf\ , r'l , I i /Θ -J - - 1i7 m with shadow 1 e map right knot image value like ue under F 4) take 4) D) (2 and lose the first will not be (20alu into one and the shadow of the shadow nal right fruit l (B3 (C3CB ο ί 牛 牛 "® (send π 考 成 成 Va block out} image will be 04V and発F F FF 义 D 过 如 如 如 如 I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I I The back piece 1X1U out 50B3 from C2B3, through it (1 into 12 like to say (P shadow in the right area of the most map (pva got about FCCFCFC I am the current case like loss (2; «] >'> ; tj bm j 4 /τ Jt Βί - pattern in the photo area of the fruit block (after p area h area a) When the image like F is like 1 if "_r,T y, -yIF ίΐΛ .r· .1 * fl) J x#l\ I \Jr ___ 式区利案 C"舄块 pictures and a district ^ Analysis of the image of the block, divided into 分 分 分 , 象 象 象 象 象 象 象 象 象 象 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式 式2 (, e a 顼 P] object, the block of the image force (8, ^ (and then &^; ^ ^ out of block 1 (after the square value shadow and. The area-style 2 y U block ϋ 』 』 ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” ” The following is the same as the C11 film and the image of the d and the difference between the image and the difference between the use of the test - :.,, / more than 4 on the test and out of the short-selling in the use of the test, 4) get the base M, " l,: The loading area has a scene 2, the value of the V-shaped block shadow 02 U-shaped element el into the area, q of the Thai reduction (2 pieces of F-like image IX component force L *) * block 4) after the profit (C Compared with the body (1) frequency conversion rate, that is, the phase contrast image xe body), the pi of the block is obtained (B when the wave is used and the same side {k-recognition is used to replace the Ca3 with the partition (P1UBFC he (CFC area left and F (, the value of Va is h, its F, the image of the added pixel 1 is shown in Figure 11) \-/ : i > The value of the image will be 02 phase diagram and medium, the value will be El, like the h image will be the same as the prime (2e) into a block} time lxe) take 32) shadow on the graph of the low C formula} between the image. (Δ shadow of the empty F specometry
Y rx 圖由本函;|/ 二,有彳 J 式含-歹| 2纟勿代 合物來 特— 影料圖 比資如 類像; i/影像 4匕圖 的 > ο M290286 下列函數可以將圖像轉成波型表示式: a.二維空間波型函數: |〇 x2+y2^〇 l〇〇 x2+j^:0 作,少)= ^f(x)S(x-a)dx = f(a) 〇0The Y rx diagram is composed of this letter; | / 2, there are 彳 J type containing - 歹 | 2 纟 代 代 代 — — 影 影 影 影 影 影 影 i 290 290 290 290 290 290 290 290 290 290 290 290 290 290 290 290 290 290 290 290 290 290 290 290 290 Convert the image into a waveform representation: a. Two-dimensional spatial waveform function: |〇x2+y2^〇l〇〇x2+j^:0, less)= ^f(x)S(xa)dx = f(a) 〇0
Ji Jv2o,淋办=1 S\ax,by) = ^S\x,y) δ\χ,γ) = δ(χ)δ(γ) b.三維空間波型函數: 5⑽⑼你) 作,加作)={士;:;:: \^\^\Zj\x,y,z)dxdydz = \ M290286 s !lf! f /1— if ry lift pJi Jv2o, 淋办=1 S\ax,by) = ^S\x,y) δ\χ,γ) = δ(χ)δ(γ) b. Three-dimensional spatial wave function: 5(10)(9) you) ()) ={士;:;:: \^\^\Zj\x,y,z)dxdydz = \ M290286 s !lf! f /1— if ry lift p
X >1 替 V 函 型 波 間 空 維 多 更 是 或 維 四 式 型 的 數 函 充 限 無。 以性 可確 們正 我的 ,果 式結 公析 的分 迷像 上影 用加 套增 並 實 d 數 函 換 轉 J5I 間 空 型 波 與 間 空 G(x, t χ,Ο) = ^Φη(χ, ί)Φη (χ,Ο) 4^)]=Σ S{x — xi gX >1 is more or less than the V-type wave. The sex can be confirmed by me, the fruit-like analysis of the fan-like image is added with the set and the real d-number is used to convert the J5I space-wave and the space G (x, t χ, Ο) = ^ Φη(χ, ί)Φη (χ,Ο) 4^)]=Σ S{x — xi g
jPF^dx = \\Asx^y)-f2^y)\^A δ(χ) = lim ->0jPF^dx = \\Asx^y)-f2^y)\^A δ(χ) = lim ->0
:J~7T d.轉換對照空間圖: 9 M290286:J~7T d. Conversion control space map: 9 M290286
R 脅' 時意 法即用 算及使 演尋加 殊搜增 特庫而 之料標 型資目 類低期 此降預 用大者 利大用 以使 演 型 波 如 效 間 時 的 對。 比願 可成 們達 我, ,率 2擷輸^匕 此1 f J ^ ,J C別將辨以輸’ 的可成位 圖分,像f當Λ空ί者即算ί 如,中影像at型標两¾換ί ;式庫的影hJ波W對原Λ’ 2模料上將“ rJ)¥J ί台的3置sinj 式 動 :At - YJ刁 3 i I 导巧=波影由32點縱 f哉成入時。料2 Ji標追 座之 之 式财 動咨 移.St 可標 力 多同影AJ型像影 .^ν' 二 J : rpt10y 重角像能表完像並la18縱點料 > 3 is^! p 2 追標資 馬蹤 追 系 達 h対f運成為U波的(2體對及將 介合為受的疊以物buu 我料相作"成人果juieH ,次貝到統後結定識傳同 式像送U然出W辨訊置 人的料軟式後h受k並識送過Μ 輸度資的示成綠將te}辨並透纟、 度f平步波準ς式快時結置果 角t㈣同合標2示來此算。裝吉 同在硬並複對像表式。運果 不存軟,%影型方Λ果收葉 結接比 移 傳位 所標 據座 艮的 i定 裝指 統到· 系台:達π 置」 M290286 【實施方式】 ^ ^每'如例·整合式物體追蹤裝置,請參閱第三 圖,本實施例包括: (1 ^ ί像辨識追縱功能的軟體系統及其軟體執行 二nrTn’产7人臉追縱辨識系統及PC裝置及Windows 2000軟體作業系統; ❿位/類比影像儲存裝置,如硬碟機; 4 動+式之追蹤馬達系統裝置及置物平台; 機及影像:比取〜像擷取傳送及接收裝置’如攝影 ⑸傳U傳送及接收震置’如,32傳輸介面及 接收裝置 及影像訓 系統裝置 訓練過之 識出來之 306)並將 裝置主要 傳送接收 數位/類比影像擷取傳送及 ^ #)對某一物體做多維影像取樣 過可移動式之追蹤攝影機之馬2 2二8) t追蹤及由軟體系統辨識(3〇4)已經 物體,§追蹤辨識完成後,便 物體影像儲存下來為旦彡後妙〇、工迫敗辨 ί伞傳送及接收裝置傳送出去; 用k在於追蹤及辨識已經學 相關訊息。 自尥的衫像,亚 流程步驟如下: (302 £ (2 )將輸入的影像資料傳之影像育料輸入; (303)上的影像辨識追蹤1^·目關的軟硬體平台 算,同時存取此軟硬體平力台mnt(3〇4)作運 像儲存裝置(3〇5及 11 M290286 川6)來做對比,並對 結果換算成定位座^ &奴追縱辨識的特定物體之運算 (3) 將定位座標U粗 (3〇7)傳回可移動式之^苁变今f訊傳送及接收裝置 (4) 可移動式之、自追如馬達系統裝置,· 回的定位座標點資統裝置(3〇8)根據所傳 置; 十移動置物平台到指定的座標位 ⑸繼績從流程(1 )重新開始全部流程。 在第一實施例中,主- 因此可以自成一個—要敕的70件全部都在同一裝置内, 物體的目的,並押=二,平台完成搜尋及辨識特定 能。 工制攝影機位置完成自動搜尋的功 請參閱第二ΐ例本體追蹤之馬達平台裴置 Π、公你 I只施例包括: (2) ? 能的軟體系統; (3) 資訊傳^芬^蹤馬達系統裝置及置物平台; 傳輸線 收裝置,如RS232傳輸介面石 影體;為物完傳已類式 比硬等能一算統識4/動 類軟置功某運系辨“移 1L/的裝置對台體及 可 ί關f裝,平軟蹤U過 4相4;置體過追㈣透 Μ在統台Η來^並 ,運ί,ίΛ裝為功 置4人硬枝述Η統能的 裝合嵌軟i上象系功置 台結d的W由ί達要裝 平置^關I藉0馬主收 的裝Ϊ相“並Η縱其接 ίϊ在ί樣if及 獨接U也U取釘之體送 個及pc^置h像、,式物傳 |送-?裝/|彩練動之取 是傳如存位維訓移過擷 置取上儲數多像可練像 裝擷台像由做影到訓影 此像平影經體成送經比 M290286 j以動怨追蹤影像。 流程步驟如下: τ-Η COV (o A (4輸 位 數 的 合 SU 由 物 定 特 有 含 將 置04 裝(4 收面 接介 及輸 送傳 傳過 取透 擷料 像次貝 影像 比影 類之 人W硬”位位險 輸Μ軟對定定W02移點 將上此比成將^(4可標 /-Ν 取做算 置/^ 座·, (203存來換(303裝(4位置(5 (4時庫果(4統定位 的 辨 像 並參 識卜於 資路之 像追台欲 料功影 點 台同料結 平,資算 體算像運 硬運影之 軟作的體 的統中物 關系置定 相體裝特 到軟存的/ 送的儲識 專能象辨 彳彳蹤 追 置系 裝達 收馬 接蹤 及追 送之 傳式 訊動 資移 過可 透給 料傳 資5) ΐ ο 黑4 的標 回座 傳的 所定 據指 根到 置1 裝4 統厶口 系平 達物 馬置 縱動 追移 之, 式料 動資 ‘程 流 部 全 始 新 ιΐΩΐιΙ ΛΙ7 1X x(x 程 流 從 續 繼 在第二實施例中,主要的元株 _ 利用馬達系统卢 1疋—個可接收訊息然4 ;擷取裝置以下可左自右以^ 有之影像擷取裝置完成自動追蹤移能統幫助 3、第二實施例:圖像資料庫索 閱第五圖,本實施例包括:家引衣置其糸統,請) 13 M290286 (2)影像儲存裝置,如 機及影像擷取卡;°傳运I接收裝置,如攝影 ()傳C及接收裝置’ * rs232傳輸介面及 此裝置可以透 送及接收裝置 練’並透過可 蹤及由軟體系 蹤辨識完成後 存下來在影像 資訊傳送及接 蹤及辨識已經 在此實施例中 統0 比影像摘取(502及510)傳 移動' 十夕!1做多維影像取樣及影像訓 馬達系統裝置(508)來追 、、’ (4)已經訓練過之物體,當追 二將穿=蹤辨識出來之物體影像儲 ϊίΐϊ:出去;裝置主要用途在於追 Γ主白ir#的、f像,並傳送接收相關訊息。 、的功處為圖像搜尋及索引系 流程步驟如下: (1) 由配合的數位/類^卜旦彡μ (5〇2及51(0將含有特定物取傳送及接收裝置 (2) 將輸人的影像tU^i1之影像資料輸人; (503)上的影像辨識%功%相^的軟硬體平台 算,同時存取此軟硬體平體系統(504)作運 506)來做對比,並對於欲+^^^^^#存5/^5〇5 ^ 結果換算成定位座標點;、從辨識的特定物體之運算 (3) 將定位座標點資料透 次“ (5〇7)傳回可移動式之追及接收裳置 M290286 U)可移動式之追蹤馬達系統裝 (5 )繼績從流程(1 )重新開始全邱、、☆ · (6)整體過程中,會產生—個相旦 對資料庫,其功能在於儲存相對應3 r匕資料庫來搜尋影像資料,減低人以S可利 搜尋相關影像的步驟及時間。 頌便用肉眼一一 在第二實施例中,主要表達的是一個 ίί ΐίί資式(511)。當影像資料庫被建f ;"/1ΐ t - ^ ^ ^ ^ _,在圖像上-點兩V:%二:以 影像=料串流檔就會被由那個始點開 ^' ?;ί2ΐ低吏用旦者搜尋的時間,而不需要二 毛、叟哥,/、中,衫像索引資料庫的格式包含:与 像,像本身、日時分秒#時間標記、 像^ 流檔(則刪⑴或是其他影像流,格式) 像串 表 代 取 徵 特 的 體 物 定 特 為 部 臉 以 ]口 3. 丟 明 :r> L Ϊ習 說明係 單說} 簡單(a。 式簡圖圖 圖式一意 f圖第示 _ 像取 圖圖辨 圖像 析意縱 之圖 分示追 度之 塊驟體 角度 區步物 同角 像行性 不同。影執合 示不圖之之整 之 朵表 倉倉乍 習知b本本彳 倉 像係f;係係 } }賓 r-s }廊。 (bcc像(acb係圖 圖圖圖圖圖圖意 一 一的二二三示 第第中第第第施 if 〇 圖料 意資 示在 樣後 取樣 實 置 裝 用 應 識 15 M290286 ^ ^圖係本創作之獨立式移動平台應用裴置實施示 第五圖(a)係本創作之圖像搜索系統資料庫每加 示意圖。 平κ她木構 第五圖(b)係本創作之圖像搜索系統資料庫索弓丨示意 圖。 '、 w 【主要部分代表符號說明】 〔習知〕 1 0 1圖像特徵取樣示意圖 1 0 2正面角度圖像取樣示意圖 „ 1 0 3左側角度圖像取樣示意圖 1 04右侧角度圖像取樣示意圖 1 0 5圖像資料庫示意圖 〔本創作〕The R-threat's method is used to calculate and optimize the search for the special type of inventory. The lower-level of the target is used to make the wave of the effect wave. If you want to be up to me, the rate is 2 撷^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Type mark two 3⁄4 for ί; type library shadow hJ wave W on the original Λ ' 2 mold material on the "rJ) ¥ J ί Taiwan's 3 set sinj type: At - YJ刁3 i I guide = wave shadow by 32 points vertical 哉 哉 。 。 料 料 Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji Ji La18 vertical point material > 3 is^! p 2 chasing the standard horse trailing chasing system h対f shipped into U wave (2 body pairs and will be the interface of the subject of the object buu I expected " Adult If juieH, after the second shell to the unified system, the same type of image is sent to the U, and then the W-recognition of the person is soft, and then the subject is sent by the k and the confession is sent. , degree f flat step wave quasi-ς fast set knot fruit angle t (four) with the standard 2 shows this calculation. Packing Ji is in the hard and complex object form. The fruit is not soft, the % shadow square fruit harvest The leaf junction is the same as that of the shifting position. The i-finished fingertips to the base: to the π setting" M290286 [Embodiment] ^ ^Every example For the combined object tracking device, please refer to the third figure. This embodiment includes: (1 ^ ί software system for identifying the tracking function and its software implementation. 2 nrTn' production 7 face tracking identification system and PC device and Windows 2000 software Operating system; / position/analog image storage device, such as hard disk drive; 4 moving + type tracking motor system device and storage platform; machine and image: comparison ~ image capture transmission and receiving device 'such as photography (5) transmission U transmission And receiving the shock 'such as 32 transmission interface and receiving device and imaging training system device training 306) and the device mainly transmits the receiving digital / analog image capture transmission and ^ #) do a multi-dimensional image of an object Sampling the movable tracking camera horse 2 2 2 8) t tracking and identification by the software system (3〇4) already objects, § tracking identification is completed, the object image is stored for the aftermath The ugly ugly transmission and receiving device transmits it; the k is used to track and identify the learned information. The self-sliding shirt image, the sub-process steps are as follows: (302 £ (2) The input image data is transmitted to the image breeding input; (303) The image recognition tracking is performed on the software and hardware platform of the target. Access this soft and hard flat force table mnt (3〇4) for image storage device (3〇5 and 11 M290286 川6) for comparison, and convert the result into a specific position of the positioning block ^ & Operation of the object (3) Transfer the positioning coordinate U coarse (3〇7) back to the movable type. The transmission and reception device (4) is movable, self-tracking, such as the motor system device, The positioning coordinate point device (3〇8) is based on the transmission; the ten mobile storage platform to the designated coordinate position (5) resumes the entire process from the process (1). In the first embodiment, the master - therefore can Into one—the 70 pieces to be smashed are all in the same device, the purpose of the object, and the second is, the platform completes the search and identifies the specific energy. For the work of the camera position to complete the automatic search, please refer to the second example body tracking. The motor platform is set to Π, and you only have one example: (2) • Software system capable; (3) Information ^Fen tracking motor system device and storage platform; transmission line receiving device, such as RS232 transmission interface stone shadow body; for the completion of the object has been analogous than the hard can be a unified knowledge 4 / dynamic class soft work a certain department Move 1L/ device to the platform and can be installed, flat soft U through 4 phase 4; body over chasing (four) through the 统 in the Taiwanese to ^ and, ί, Λ Λ installed for the function of 4 people hard枝 能 能 能 嵌 嵌 嵌 嵌 嵌 嵌 由 由 由 由 由 由 由 由 由 由 由 由 ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί ί U is also U to take the nail body to send a pc and set h image,, the style of the transmission | send -? loaded / | color training is taken as the storage of the training, the transfer of the 撷 取 取 取 取 取It can be used to make a picture like a shadow to the training. This image is like a flat shadow. It is more than M290286 j to track the image. The process steps are as follows: τ-Η COV (o A (4 input digits of SU) The object will be equipped with a set of 04 (4 face-to-face contact and conveyance pass-through data such as the sub-shell image than the shadow class of the person W hard) position insurance soft pair fixed W02 shift point will be on this ratio Cheng will ^ (4 can be marked / - Ν take the calculation / ^ seat ·, (203 To change (303 installed (4 position (5 (4 time kuguo (4 unified positioning of the image and participate in the knowledge of the image of the road to chase the Taiwanese desire to see the work of the same point with the same material, the calculation of the image The hard-working shadow of the soft body of the system is set to the phase of the body to install the soft storage / send the storage of the special ability to identify the traces of the chasing system to the horse to catch and chase The news has been transferred to the transparent feedstock. 5) ΐ ο Black 4's back-to-back pass is based on the roots of the set-up, and the 4th 厶 系 系 平 平 平 平 平 , , , , , , , , , , , , , 'Chengliu Department all new ΐ ΐ ΐ Ι Ι 1 7 1X x (x process flow from the continuation in the second embodiment, the main element _ using the motor system Lu 1 疋 - can receive the message then 4; The image tracking device is used to complete the automatic tracking and shifting system. 3. The second embodiment: the image database is read in the fifth figure. This embodiment includes: the home clothes are placed on the system, please) 13 M290286 ( 2) Image storage device, such as machine and image capture card; °Transport I receiving device, such as photography () transmission C and receiving device' * rs232 transmission And the device can be used to transmit and receive devices and pass through the traceability and identification by the soft system. After the image information transmission and the identification and identification, it has been extracted in this embodiment (502 and 510). Passing the mobile 'Ten eve! 1 Do multidimensional image sampling and image training motor system device (508) to chase,, ' (4) already trained objects, when chasing two will wear the trace of the object image stored ϊ ΐϊ: Go out; the main purpose of the device is to trace the image of the main white ir#, and send and receive related information. The steps of the image search and indexing process are as follows: (1) The digits/classes of the mating 彡μ (5〇2 and 51 (0 will contain the specific object to take the transmission and receiving device (2) The image data of the input image tU^i1 is input; the image on the (503) is identified by the software and hardware platform of %%%, and the software and hardware system (504) is accessed 506) For comparison, and for the desire +^^^^^# save 5/^5〇5 ^ the result is converted into the positioning coordinate point; the operation from the identified specific object (3) will be the positioning coordinate point data through the "(5〇 7) Returning to the portable type of catching and receiving skirts M290286 U) Removable tracking motor system installed (5) Succession from the process (1) restarts all Qiu, ☆ · (6) In the overall process, it will be generated A matching database, the function of which is to store the corresponding 3 r匕 database to search for image data, and to reduce the steps and time for the person to search for related images by S Keli. The naked eye is used in the second embodiment. The main expression is an ίί ΐ ί 资 (511). When the image database is built f; "/1ΐ t - ^ ^ ^ ^ _, on the image - point two V:% two: shadow = The stream file will be opened by the starting point ^' ?; ί2 ΐ low-time search time, without the need for Ermao, 叟哥, /, 中, shirt like index database format contains: and , like itself, day, hour, minute, second, time mark, like ^ stream file (then delete (1) or other video stream, format). The body object of the string table is specially selected as the face of the face. r> L 说明 说明 系 } } } } } } } 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单 简单The same angle is different from the line. The shadows are not shown in the figure. The warehouse is like a warehouse. The book is like a f; the system is a } } guest rs } gallery. (bcc image (acb diagram) Figure 2, Figure 2, Figure 2, 2nd, 2nd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd The fifth figure (a) is the schematic diagram of the image search system database of this creation. The fifth figure of the κ her wood structure (b) is the creation Image search system database library bow diagram. ', w [main part representative symbol description] [study] 1 0 1 image feature sampling schematic 1 0 2 front angle image sampling schematic „ 1 0 3 left angle image Sampling Schematic 1 04 Right Angle Image Sampling Schematic 1 0 5 Image Database Schematic [This Creation]
201比對區塊圖形a 202比對區塊圖形B 2 0 3比對區塊圖形c 2 0 4比對區塊圖形d 211資料輸入程序:取樣臉部所有資料完成資料輸入 212資料轉化程序:將資料由實體空間轉化到波型空 間(Real space->Wave space) 21 3多重取樣程序:重覆多重取樣臉部資料並轉化成 波形 214波型合成程序·· a波+B波+C波=複合波 2 1 5文測資料輸入程序:輸入受測臉部影像資料 2 1 6空間函數轉換程序:轉化成波形空間之函式 2 1 7波型形成圖案 218波型比對程序:受測資料VS·比對資料(複合波) 2 1 9波型比對結果:確認波形比對之相似性結果 16 M290286201 alignment block graphic a 202 comparison block graphic B 2 0 3 comparison block graphic c 2 0 4 comparison block graphic d 211 data input program: sampling face all data completion data input 212 data conversion program: Converting data from physical space to waveform space (Real space->Wave space) 21 3Multisampling procedure: Repeating multi-sampled facial data and converting it into waveform 214 waveform synthesis program·· a wave + B wave + C Wave=composite wave 2 1 5 text data input program: input the measured face image data 2 1 6 space function conversion program: function into waveform space 2 1 7 wave pattern forming pattern 218 wave type comparison program: subject VS·Comparative data (composite wave) 2 1 9 wave type comparison result: confirm the similarity of waveform comparison result 16 M290286
307資訊傳送裝置 308馬達及平台 31 0波型比對程序 220結果判斷程序··由門檻 301特定物體圖像 置物平台可以上下、左右移動 309 RS232傳輸介面 4 0 1置物平台··置$ 4 0 2馬達裝置 403 PC及其他硬體資訊傳輸裝置 ;ι面傳輸線USB 405介面傳輸線RS232 6平台上的攝影機 — 5〇1 2定物體圖像 5〇2攝影機 5 〇 3衫像擷取裝置(影像擷取卡及相關裝置) 5〇4 PC裝置及軟體作業系統 5〇5,像铸存裝置 506影像資料庫 507資訊傳送裝置 508馬達及平台 509介面傳輸線RS232 51 0鏡頭 5 ^圖像搜索系統資料庫索引示意圖:每一筆圖像資 料都含有時間資訊(日:時:分:秒) 17307 information transmission device 308 motor and platform 31 0 wave type comparison program 220 result judgment program · By threshold 301 specific object image storage platform can move up and down, left and right 309 RS232 transmission interface 4 0 1 storage platform · · $ 4 0 2 motor device 403 PC and other hardware information transmission device; ι surface transmission line USB 405 interface transmission line RS232 6 platform camera - 5 〇 1 2 fixed object image 5 〇 2 camera 5 〇 3 shirt image capture device (image 撷Cards and related devices) 5〇4 PC device and software operating system 5〇5, like casting device 506 image database 507 information transfer device 508 motor and platform 509 interface transmission line RS232 51 0 lens 5 ^ image search system database Index diagram: Each image data contains time information (day: hour: minute: second) 17
Claims (1)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW93218725U TWM290286U (en) | 2004-11-22 | 2004-11-22 | Storage and applied devices based on images obtained from object tracking and recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW93218725U TWM290286U (en) | 2004-11-22 | 2004-11-22 | Storage and applied devices based on images obtained from object tracking and recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| TWM290286U true TWM290286U (en) | 2006-05-01 |
Family
ID=37587704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| TW93218725U TWM290286U (en) | 2004-11-22 | 2004-11-22 | Storage and applied devices based on images obtained from object tracking and recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| TW (1) | TWM290286U (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7860271B2 (en) | 2006-09-05 | 2010-12-28 | Zippy Technology Corp. | Portable image monitoring and identifying device |
| TWI447544B (en) * | 2007-09-04 | 2014-08-01 | Musashi Engineering Inc | A memory medium, a device, and a computer program that has a program that creates a mobile program |
| US8885876B2 (en) | 2008-04-18 | 2014-11-11 | National Taiwan University | Visual tracking system and method thereof |
| TWI490735B (en) * | 2010-01-20 | 2015-07-01 | Silicon Integrated Sys Corp | Multiple fingers touch sensing method using matching algorithm |
| US9357174B2 (en) | 2012-04-09 | 2016-05-31 | Intel Corporation | System and method for avatar management and selection |
| US11295502B2 (en) | 2014-12-23 | 2022-04-05 | Intel Corporation | Augmented facial animation |
| US11303850B2 (en) | 2012-04-09 | 2022-04-12 | Intel Corporation | Communication using interactive avatars |
| US11887231B2 (en) | 2015-12-18 | 2024-01-30 | Tahoe Research, Ltd. | Avatar animation system |
-
2004
- 2004-11-22 TW TW93218725U patent/TWM290286U/en not_active IP Right Cessation
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7860271B2 (en) | 2006-09-05 | 2010-12-28 | Zippy Technology Corp. | Portable image monitoring and identifying device |
| TWI447544B (en) * | 2007-09-04 | 2014-08-01 | Musashi Engineering Inc | A memory medium, a device, and a computer program that has a program that creates a mobile program |
| US8885876B2 (en) | 2008-04-18 | 2014-11-11 | National Taiwan University | Visual tracking system and method thereof |
| TWI490735B (en) * | 2010-01-20 | 2015-07-01 | Silicon Integrated Sys Corp | Multiple fingers touch sensing method using matching algorithm |
| US9357174B2 (en) | 2012-04-09 | 2016-05-31 | Intel Corporation | System and method for avatar management and selection |
| TWI646498B (en) * | 2012-04-09 | 2019-01-01 | 英特爾股份有限公司 | System and method for avatar management and selection |
| TWI656505B (en) * | 2012-04-09 | 2019-04-11 | 英特爾股份有限公司 | System and method for avatar management and selection |
| US11303850B2 (en) | 2012-04-09 | 2022-04-12 | Intel Corporation | Communication using interactive avatars |
| US11595617B2 (en) | 2012-04-09 | 2023-02-28 | Intel Corporation | Communication using interactive avatars |
| US12556659B2 (en) | 2012-04-09 | 2026-02-17 | Intel Corporation | Communication using interactive avatars |
| US11295502B2 (en) | 2014-12-23 | 2022-04-05 | Intel Corporation | Augmented facial animation |
| US11887231B2 (en) | 2015-12-18 | 2024-01-30 | Tahoe Research, Ltd. | Avatar animation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108305317B (en) | Image processing method, device and storage medium | |
| JP6151323B2 (en) | Dynamic template tracking | |
| US10936537B2 (en) | Depth sensing camera glasses with gesture interface | |
| US12306910B2 (en) | System and method for markerless motion capture | |
| Wu et al. | Eaglesense: Tracking people and devices in interactive spaces using real-time top-view depth-sensing | |
| US20140270363A1 (en) | 3D Visual Proxemics: Recognizing Human Interactions in 3D From a Single Image | |
| GB2403363A (en) | Tags for automated image processing | |
| JP2015090553A (en) | Terminal apparatus, additional information management apparatus, and additional information management method | |
| KR20150105308A (en) | Operating environment with gestural control and multiple client devices. displays, and users | |
| TW201541407A (en) | Method for generating three-dimensional information from identifying two-dimensional images | |
| CN108416832A (en) | Display methods, device and the storage medium of media information | |
| CN103106236A (en) | Information registration device, information registration method, information registration system, information presentation device, informaton presentation method and informaton presentaton system | |
| TWM290286U (en) | Storage and applied devices based on images obtained from object tracking and recognition technology | |
| WO2013140678A1 (en) | Information processing system | |
| TWM482797U (en) | Augmented-reality system capable of displaying three-dimensional image | |
| JP6323548B2 (en) | Imaging assistance system, imaging apparatus, information processing apparatus, imaging assistance program, and imaging assistance method | |
| JP2013111188A (en) | Trading card game method, program, and recording medium | |
| Tadesse et al. | Privacy-aware human activity recognition from a wearable camera: highlights from the IEEE video and image processing cup 2019 student competition [sp competitions] | |
| JP7160707B2 (en) | Method for providing images containing virtual characters | |
| CN115550563B (en) | Video processing method, device, computer equipment and storage medium | |
| JP6958795B1 (en) | Information processing methods, computer programs and information processing equipment | |
| JP2013238987A (en) | Information display device, information input device, information display program, and information input program | |
| WO2019052374A1 (en) | Information display method and device | |
| CN206585648U (en) | Electronic device and electronic system capable of generating augmented reality images | |
| Chong et al. | Visual 3d tracking of child-adult social interactions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| MM4K | Annulment or lapse of a utility model due to non-payment of fees |